TOP ACTIVATIONS
MAX = 6.307

one . 00 96 275 . g 001 Pre - training
pur ak ushi Profile Joined August 2012 United States 3
Ko Do Profile Joined December 2010 United States 6
org / index . php ? topic = 28 18 48
p one . 00 96 275 . g 001 Pre -
polit ically correct o omp a lo omp as for
J aaaa asper Profile Blog Joined April 2012 United States 5
2 - 1 / 2 "] [ EC O " A
K ier an Profile Blog Joined August 2011 United States 6
re i Profile Blog Joined October 2002 United States 3
little as $ 2 a month ! Support Progressive
Big Fan Profile Blog Joined December 2010 TL AD T
of Dal K Profile Blog Joined June 2012 Canada 16 10
ada ver BB Profile Blog Joined June 2009 Germany 247 34
. 00 96 275 . g 001 Pre - training .
as well . <|endoftext|> HA V ANA ( Reuters ) -
image larg er image T IFF original image Download
rock - favorite favorite favorite favorite - December 13 , 2010
the Clojure subset of the GitHub dataset . I did this
Dark horse Profile Blog Joined December 2011 United States 228

MIN ACTIVATIONS
MIN = -6.825

make ? The same arguments Ign at ie ff is making
phone in phones "> < span ng - bind =" phone
< T > { pub fn new ( t : T
null atomic pointer . pub fn null () -> Atomic <
Hide Caption 4 of 15 Photos : Carly Fiorina 's political
Phone List Ctrl "> < ul > < li ng -
bright about the devastating sanctions Washington imposed on Iraq after the
Hide Caption 7 of 15 Photos : Carly Fiorina 's political
{ const float f Mass = ( m D ensity +
Hide Caption 5 of 15 Photos : Carly Fiorina 's political
impl Board { pub fn copy _ board ( &
Hide Caption 12 of 15 Photos : Carly Fiorina 's political
the must - pass measures Congress will take up when it
The Chronicle 3 of 15 Photo : Le a Suzuki ,
< T > { pub fn load < ' a >
. Disclaimer : © 2015 Money Morning and Money
a video with # Ask The D ubs , then tune
< body ng - controller =" Phone List Ctrl "> <
Hide Caption 6 of 15 Photos : Carly Fiorina 's political
The Chronicle 4 of 15 Photo : Le a Suzuki ,

INTERVAL 3.024 - 6.307
CONTAINS 0.245%

: report Vietnamese airline takes steps to open flights to US
( 5 s )} Kh 7 { ( 150 s )}
м н и к о� а
) and obesity / over weight trends in all 53 of
: <|endoftext|> Court documents reveals Bungie 's plans for Destiny ,

INTERVAL -0.259 - 3.024
CONTAINS 61.566%

doesn t have layers . He doesn
for all the new signings to start contributing right away ,
Aram Sar oy an s oxy gen
Romney was obviously more closely associated with Bain Capital than
and it was everywhere . THE PUR GE D

INTERVAL -3.542 - -0.259
CONTAINS 38.093%

to " sky rocket ," and his recent town - hall
ness and a historian of culture , he summed up Z
to be , and I knew my husband was doing this
Wall Street , or whether Wall Street will continue to wre
the people we couldn 't allow ourselves to be accepted by

INTERVAL -6.825 - -3.542
CONTAINS 0.096%

. tv / d anks h rine Weekly SC 2 Podcast
f ); RAW _ ASS ERT ( it -> f ()
royalty ? @ A jit P ai F CC orp Sh
) O pin ion ( by Jesse Smith )
billion years after the Big Bang .
Tokenone
Token ID505
Feature activation+1.12e+00

Pos logit contributions
interstitial+0.310
apult+0.304
anth+0.300
colored+0.297
 Title+0.285
Neg logit contributions
 contrace-0.336
 dstg-0.309
 Krishna-0.291
 Mississ-0.286
 Dru-0.284
Token.
Token ID13
Feature activation+4.42e+00

Pos logit contributions
interstitial+0.812
apult+0.801
anth+0.791
colored+0.782
 Title+0.760
Neg logit contributions
 contrace-0.978
 dstg-0.873
 Krishna-0.825
 Mississ-0.816
 Dru-0.808
Token00
Token ID405
Feature activation+4.28e+00

Pos logit contributions
interstitial+2.692
apult+2.614
anth+2.586
colored+2.546
 Title+2.449
Neg logit contributions
 contrace-4.322
 dstg-3.997
 Krishna-3.801
 Mississ-3.762
 Dru-3.745
Token96
Token ID4846
Feature activation+4.19e+00

Pos logit contributions
interstitial+2.757
apult+2.713
anth+2.690
colored+2.662
 Title+2.609
Neg logit contributions
 contrace-4.055
 dstg-3.691
 Krishna-3.444
 Mississ-3.421
rists-3.402
Token275
Token ID23195
Feature activation+5.79e+00

Pos logit contributions
interstitial+2.773
apult+2.720
anth+2.692
colored+2.656
 Title+2.600
Neg logit contributions
 contrace-3.888
 dstg-3.537
 Krishna-3.310
 Mississ-3.277
 Dru-3.267
Token.
Token ID13
Feature activation+6.31e+00

Pos logit contributions
 Title+3.699
interstitial+3.566
colored+3.498
apult+3.489
anth+3.461
Neg logit contributions
 contrace-5.582
 dstg-4.968
rists-4.758
 Dru-4.600
 Mississ-4.575
Tokeng
Token ID70
Feature activation+5.26e+00

Pos logit contributions
interstitial+3.695
apult+3.651
colored+3.637
anth+3.632
 Title+3.527
Neg logit contributions
 contrace-6.250
 dstg-5.689
 Krishna-5.477
 Dru-5.459
 Mississ-5.338
Token001
Token ID8298
Feature activation+4.69e+00

Pos logit contributions
interstitial+2.315
apult+2.305
 Title+2.254
anth+2.249
colored+2.184
Neg logit contributions
 contrace-6.029
 dstg-5.492
 Krishna-5.380
 Dru-5.285
 Mississ-5.241
Token Pre
Token ID3771
Feature activation+6.44e-01

Pos logit contributions
interstitial+2.847
apult+2.842
 Title+2.773
colored+2.756
anth+2.743
Neg logit contributions
 contrace-4.511
 dstg-4.134
rists-3.881
 Krishna-3.844
 Mississ-3.808
Token-
Token ID12
Feature activation+4.14e-01

Pos logit contributions
interstitial+0.469
apult+0.458
anth+0.448
colored+0.447
 Title+0.430
Neg logit contributions
 contrace-0.553
 dstg-0.515
 Krishna-0.482
 Mississ-0.477
 Dru-0.474
Tokentraining
Token ID34409
Feature activation-2.38e-01

Pos logit contributions
interstitial+0.245
apult+0.238
anth+0.232
colored+0.230
 Title+0.220
Neg logit contributions
 contrace-0.411
 dstg-0.386
 Krishna-0.366
 Mississ-0.362
 Dru-0.361
Token
Token ID198
Feature activation+7.13e-01

Pos logit contributions
interstitial+0.196
apult+0.189
anth+0.183
colored+0.182
 Title+0.172
Neg logit contributions
 contrace-0.356
 dstg-0.340
 Krishna-0.322
 Mississ-0.319
 Dru-0.318
Tokenpur
Token ID14225
Feature activation+2.17e+00

Pos logit contributions
interstitial+0.512
apult+0.497
anth+0.492
colored+0.487
 Title+0.467
Neg logit contributions
 contrace-0.623
 dstg-0.577
 Krishna-0.545
 Mississ-0.537
 Dru-0.534
Tokenak
Token ID461
Feature activation-2.31e-01

Pos logit contributions
interstitial+1.424
apult+1.384
anth+1.372
colored+1.352
 Title+1.285
Neg logit contributions
 contrace-2.033
 dstg-1.890
 Krishna-1.784
 Mississ-1.767
 Dru-1.757
Tokenushi
Token ID17731
Feature activation-1.96e+00

Pos logit contributions
 contrace+0.207
 dstg+0.193
 Krishna+0.182
 Mississ+0.180
 Dru+0.179
Neg logit contributions
interstitial-0.159
apult-0.155
anth-0.151
colored-0.150
 Title-0.145
Token Profile
Token ID13118
Feature activation+2.27e+00

Pos logit contributions
 contrace+1.805
 dstg+1.690
 Krishna+1.604
 Dru+1.583
 Mississ+1.583
Neg logit contributions
interstitial-1.292
apult-1.252
anth-1.215
colored-1.215
 Title-1.156
Token Joined
Token ID16709
Feature activation+6.00e+00

Pos logit contributions
interstitial+1.587
apult+1.567
anth+1.542
colored+1.519
 Title+1.500
Neg logit contributions
 contrace-1.996
 dstg-1.865
 Krishna-1.733
 Mississ-1.713
 Dru-1.697
Token August
Token ID2932
Feature activation+2.94e+00

Pos logit contributions
 Title+3.489
interstitial+3.456
anth+3.401
apult+3.375
colored+3.374
Neg logit contributions
 contrace-5.906
 dstg-5.434
rists-5.081
 Krishna-4.940
 Mississ-4.853
Token 2012
Token ID2321
Feature activation+3.14e+00

Pos logit contributions
interstitial+2.097
apult+2.073
anth+2.068
colored+2.027
 Title+2.023
Neg logit contributions
 contrace-2.557
 dstg-2.357
 Krishna-2.153
rists-2.149
 Mississ-2.109
Token United
Token ID1578
Feature activation+2.22e+00

Pos logit contributions
interstitial+1.752
apult+1.720
anth+1.677
colored+1.654
 Title+1.633
Neg logit contributions
 contrace-3.207
 dstg-3.003
 Krishna-2.805
rists-2.795
 Mississ-2.767
Token States
Token ID1829
Feature activation+3.50e+00

Pos logit contributions
interstitial+1.319
apult+1.281
anth+1.253
colored+1.244
 Title+1.205
Neg logit contributions
 contrace-2.191
 dstg-2.062
 Krishna-1.942
 Mississ-1.915
 Dru-1.907
Token 3
Token ID513
Feature activation+4.63e-02

Pos logit contributions
interstitial+1.906
apult+1.867
anth+1.819
colored+1.797
 Title+1.781
Neg logit contributions
 contrace-3.633
 dstg-3.395
 Krishna-3.180
rists-3.157
 Mississ-3.135
Token
Token ID198
Feature activation-9.62e-01

Pos logit contributions
 contrace+0.958
 dstg+0.904
 Krishna+0.861
 Mississ+0.854
 Dru+0.849
Neg logit contributions
interstitial-0.558
apult-0.536
anth-0.522
colored-0.519
 Title-0.490
Token
Token ID198
Feature activation-7.46e-01

Pos logit contributions
 contrace+0.924
 dstg+0.903
 Krishna+0.860
 Dru+0.851
 Mississ+0.850
Neg logit contributions
interstitial-0.582
apult-0.555
anth-0.531
colored-0.528
 Title-0.494
TokenKo
Token ID48735
Feature activation-5.36e-01

Pos logit contributions
 contrace+0.654
 dstg+0.612
 Krishna+0.575
 Mississ+0.567
 Dru+0.566
Neg logit contributions
interstitial-0.525
apult-0.513
anth-0.499
colored-0.496
 Title-0.481
TokenDo
Token ID5211
Feature activation-1.00e-01

Pos logit contributions
 contrace+0.481
 dstg+0.449
 Krishna+0.423
 Mississ+0.418
 Dru+0.416
Neg logit contributions
interstitial-0.368
apult-0.359
anth-0.351
colored-0.349
 Title-0.336
Token Profile
Token ID13118
Feature activation+2.99e+00

Pos logit contributions
 contrace+0.090
 dstg+0.084
 Krishna+0.079
 Mississ+0.078
 Dru+0.078
Neg logit contributions
interstitial-0.069
apult-0.068
anth-0.066
colored-0.066
 Title-0.064
Token Joined
Token ID16709
Feature activation+5.98e+00

Pos logit contributions
interstitial+2.004
apult+1.974
anth+1.930
colored+1.913
 Title+1.874
Neg logit contributions
 contrace-2.703
 dstg-2.528
 Krishna-2.363
 Mississ-2.335
 Dru-2.325
Token December
Token ID3426
Feature activation+1.73e+00

Pos logit contributions
interstitial+3.467
 Title+3.429
apult+3.378
anth+3.362
colored+3.357
Neg logit contributions
 contrace-5.894
 dstg-5.446
rists-5.076
 Krishna-4.934
 Mississ-4.867
Token 2010
Token ID3050
Feature activation+1.79e+00

Pos logit contributions
interstitial+1.288
apult+1.264
anth+1.245
colored+1.235
 Title+1.211
Neg logit contributions
 contrace-1.457
 dstg-1.348
 Krishna-1.248
 Mississ-1.230
rists-1.225
Token United
Token ID1578
Feature activation+7.42e-01

Pos logit contributions
interstitial+1.035
apult+1.008
anth+0.981
colored+0.973
 Title+0.936
Neg logit contributions
 contrace-1.800
 dstg-1.692
 Krishna-1.600
 Mississ-1.582
 Dru-1.577
Token States
Token ID1829
Feature activation+2.91e+00

Pos logit contributions
interstitial+0.459
apult+0.447
anth+0.437
colored+0.434
 Title+0.417
Neg logit contributions
 contrace-0.717
 dstg-0.672
 Krishna-0.635
 Mississ-0.627
 Dru-0.625
Token 6
Token ID718
Feature activation+6.83e-02

Pos logit contributions
interstitial+1.548
apult+1.514
anth+1.475
colored+1.462
 Title+1.437
Neg logit contributions
 contrace-3.041
 dstg-2.853
 Krishna-2.676
rists-2.652
 Mississ-2.640
Tokenorg
Token ID2398
Feature activation+2.88e+00

Pos logit contributions
interstitial+1.781
apult+1.747
anth+1.717
colored+1.708
 Title+1.660
Neg logit contributions
 contrace-1.415
 dstg-1.295
 Krishna-1.197
 Mississ-1.178
 Dru-1.172
Token/
Token ID14
Feature activation+3.89e+00

Pos logit contributions
interstitial+1.982
apult+1.959
anth+1.920
colored+1.909
 Title+1.853
Neg logit contributions
 contrace-2.594
 dstg-2.379
 Krishna-2.231
 Mississ-2.209
 Dru-2.197
Tokenindex
Token ID9630
Feature activation+1.81e+00

Pos logit contributions
interstitial+1.869
colored+1.816
apult+1.814
anth+1.799
 Title+1.681
Neg logit contributions
 contrace-4.285
 dstg-4.030
 Mississ-3.845
 Krishna-3.834
 Dru-3.805
Token.
Token ID13
Feature activation+3.70e+00

Pos logit contributions
interstitial+1.371
apult+1.344
anth+1.323
colored+1.315
 Title+1.267
Neg logit contributions
 contrace-1.511
 dstg-1.385
 Krishna-1.298
 Mississ-1.287
 Dru-1.274
Tokenphp
Token ID10121
Feature activation+2.07e+00

Pos logit contributions
interstitial+2.657
apult+2.597
anth+2.558
colored+2.535
 Title+2.436
Neg logit contributions
 contrace-3.213
 dstg-2.982
 Krishna-2.800
 Mississ-2.773
 Dru-2.757
Token?
Token ID30
Feature activation+5.80e+00

Pos logit contributions
interstitial+1.418
apult+1.386
anth+1.357
colored+1.345
 Title+1.298
Neg logit contributions
 contrace-1.871
 dstg-1.743
 Krishna-1.642
 Mississ-1.623
 Dru-1.618
Tokentopic
Token ID26652
Feature activation+2.44e+00

Pos logit contributions
interstitial+2.092
colored+2.014
anth+2.006
apult+1.979
 Title+1.791
Neg logit contributions
 contrace-7.090
 dstg-6.688
 Mississ-6.419
 Krishna-6.416
 Dru-6.346
Token=
Token ID28
Feature activation+2.64e+00

Pos logit contributions
interstitial+1.614
apult+1.599
anth+1.554
colored+1.553
 Title+1.501
Neg logit contributions
 contrace-2.265
 dstg-2.090
 Krishna-1.964
 Mississ-1.955
 Dru-1.923
Token28
Token ID2078
Feature activation+2.50e+00

Pos logit contributions
interstitial+1.802
apult+1.756
anth+1.733
colored+1.711
 Title+1.659
Neg logit contributions
 contrace-2.394
 dstg-2.206
 Krishna-2.071
 Mississ-2.054
 Dru-2.041
Token18
Token ID1507
Feature activation+2.18e+00

Pos logit contributions
interstitial+1.632
apult+1.598
anth+1.572
colored+1.553
 Title+1.510
Neg logit contributions
 contrace-2.337
 dstg-2.153
 Krishna-2.027
 Mississ-2.011
 Dru-1.997
Token48
Token ID2780
Feature activation+1.20e+00

Pos logit contributions
interstitial+1.439
apult+1.409
anth+1.384
colored+1.370
 Title+1.338
Neg logit contributions
 contrace-2.020
 dstg-1.866
 Krishna-1.749
 Mississ-1.734
 Dru-1.726
Tokenp
Token ID79
Feature activation+4.06e-01

Pos logit contributions
interstitial+1.442
anth+1.396
apult+1.392
colored+1.349
 Title+1.281
Neg logit contributions
 contrace-2.835
 dstg-2.667
 Krishna-2.546
 Mississ-2.534
 Dru-2.512
Tokenone
Token ID505
Feature activation+1.12e+00

Pos logit contributions
interstitial+0.310
apult+0.304
anth+0.300
colored+0.297
 Title+0.285
Neg logit contributions
 contrace-0.336
 dstg-0.309
 Krishna-0.291
 Mississ-0.286
 Dru-0.284
Token.
Token ID13
Feature activation+4.42e+00

Pos logit contributions
interstitial+0.812
apult+0.801
anth+0.791
colored+0.782
 Title+0.760
Neg logit contributions
 contrace-0.978
 dstg-0.873
 Krishna-0.825
 Mississ-0.816
 Dru-0.808
Token00
Token ID405
Feature activation+4.28e+00

Pos logit contributions
interstitial+2.692
apult+2.614
anth+2.586
colored+2.546
 Title+2.449
Neg logit contributions
 contrace-4.322
 dstg-3.997
 Krishna-3.801
 Mississ-3.762
 Dru-3.745
Token96
Token ID4846
Feature activation+4.19e+00

Pos logit contributions
interstitial+2.757
apult+2.713
anth+2.690
colored+2.662
 Title+2.609
Neg logit contributions
 contrace-4.055
 dstg-3.691
 Krishna-3.444
 Mississ-3.421
rists-3.402
Token275
Token ID23195
Feature activation+5.79e+00

Pos logit contributions
interstitial+2.773
apult+2.720
anth+2.692
colored+2.656
 Title+2.600
Neg logit contributions
 contrace-3.888
 dstg-3.537
 Krishna-3.310
 Mississ-3.277
 Dru-3.267
Token.
Token ID13
Feature activation+6.31e+00

Pos logit contributions
 Title+3.699
interstitial+3.566
colored+3.498
apult+3.489
anth+3.461
Neg logit contributions
 contrace-5.582
 dstg-4.968
rists-4.758
 Dru-4.600
 Mississ-4.575
Tokeng
Token ID70
Feature activation+5.26e+00

Pos logit contributions
interstitial+3.695
apult+3.651
colored+3.637
anth+3.632
 Title+3.527
Neg logit contributions
 contrace-6.250
 dstg-5.689
 Krishna-5.477
 Dru-5.459
 Mississ-5.338
Token001
Token ID8298
Feature activation+4.69e+00

Pos logit contributions
interstitial+2.315
apult+2.305
 Title+2.254
anth+2.249
colored+2.184
Neg logit contributions
 contrace-6.029
 dstg-5.492
 Krishna-5.380
 Dru-5.285
 Mississ-5.241
Token Pre
Token ID3771
Feature activation+6.44e-01

Pos logit contributions
interstitial+2.847
apult+2.842
 Title+2.773
colored+2.756
anth+2.743
Neg logit contributions
 contrace-4.511
 dstg-4.134
rists-3.881
 Krishna-3.844
 Mississ-3.808
Token-
Token ID12
Feature activation+4.14e-01

Pos logit contributions
interstitial+0.469
apult+0.458
anth+0.448
colored+0.447
 Title+0.430
Neg logit contributions
 contrace-0.553
 dstg-0.515
 Krishna-0.482
 Mississ-0.477
 Dru-0.474
Token
Token ID198
Feature activation+1.82e-01

Pos logit contributions
interstitial+0.275
apult+0.267
anth+0.259
colored+0.256
 Title+0.244
Neg logit contributions
 contrace-0.516
 dstg-0.489
 Krishna-0.465
 Mississ-0.460
 Dru-0.459
Tokenpolit
Token ID34470
Feature activation+9.72e-01

Pos logit contributions
interstitial+0.129
apult+0.126
anth+0.123
colored+0.122
 Title+0.118
Neg logit contributions
 contrace-0.159
 dstg-0.148
 Krishna-0.140
 Mississ-0.138
 Dru-0.138
Tokenically
Token ID1146
Feature activation+1.04e+00

Pos logit contributions
interstitial+0.521
apult+0.505
anth+0.490
colored+0.486
 Title+0.462
Neg logit contributions
 contrace-1.019
 dstg-0.962
 Krishna-0.914
 Mississ-0.905
 Dru-0.902
Token correct
Token ID3376
Feature activation+8.73e-01

Pos logit contributions
interstitial+0.780
apult+0.762
anth+0.747
colored+0.745
 Title+0.719
Neg logit contributions
 contrace-0.873
 dstg-0.813
 Krishna-0.759
 Mississ-0.750
 Dru-0.744
Token o
Token ID267
Feature activation+1.93e-01

Pos logit contributions
interstitial+0.641
apult+0.627
anth+0.613
colored+0.610
 Title+0.589
Neg logit contributions
 contrace-0.742
 dstg-0.690
 Krishna-0.648
 Mississ-0.640
 Dru-0.637
Tokenomp
Token ID3361
Feature activation+5.67e+00

Pos logit contributions
interstitial+0.133
apult+0.129
anth+0.126
colored+0.126
 Title+0.121
Neg logit contributions
 contrace-0.173
 dstg-0.162
 Krishna-0.152
 Mississ-0.150
 Dru-0.150
Tokena
Token ID64
Feature activation+1.03e+00

Pos logit contributions
interstitial+3.163
apult+3.109
anth+3.103
colored+2.955
 Title+2.926
Neg logit contributions
 contrace-5.776
 dstg-5.401
 Krishna-5.046
 Mississ-5.019
rists-4.970
Token lo
Token ID2376
Feature activation+9.50e-01

Pos logit contributions
interstitial+0.765
apult+0.749
anth+0.734
colored+0.730
 Title+0.708
Neg logit contributions
 contrace-0.861
 dstg-0.798
 Krishna-0.749
 Mississ-0.739
 Dru-0.736
Tokenomp
Token ID3361
Feature activation+3.55e+00

Pos logit contributions
interstitial+0.346
apult+0.331
anth+0.317
colored+0.313
 Title+0.291
Neg logit contributions
 contrace-1.159
 dstg-1.101
 Krishna-1.056
 Mississ-1.046
 Dru-1.044
Tokenas
Token ID292
Feature activation+8.60e-01

Pos logit contributions
interstitial+2.197
apult+2.168
anth+2.127
colored+2.075
 Title+1.994
Neg logit contributions
 contrace-3.423
 dstg-3.193
 Krishna-3.010
 Mississ-2.988
 Dru-2.973
Token for
Token ID329
Feature activation+4.74e-01

Pos logit contributions
interstitial+0.601
apult+0.586
anth+0.573
colored+0.570
 Title+0.549
Neg logit contributions
 contrace-0.761
 dstg-0.710
 Krishna-0.669
 Mississ-0.661
 Dru-0.658
TokenJ
Token ID41
Feature activation+5.31e-01

Pos logit contributions
interstitial+0.266
apult+0.259
anth+0.254
colored+0.253
 Title+0.243
Neg logit contributions
 contrace-0.329
 dstg-0.306
 Krishna-0.288
 Mississ-0.285
 Dru-0.284
Tokenaaaa
Token ID24794
Feature activation+3.13e-01

Pos logit contributions
interstitial+0.363
apult+0.355
anth+0.348
colored+0.344
 Title+0.331
Neg logit contributions
 contrace-0.479
 dstg-0.447
 Krishna-0.421
 Mississ-0.416
 Dru-0.414
Tokenasper
Token ID32981
Feature activation-1.57e+00

Pos logit contributions
interstitial+0.212
apult+0.207
anth+0.203
colored+0.201
 Title+0.194
Neg logit contributions
 contrace-0.285
 dstg-0.266
 Krishna-0.250
 Mississ-0.248
 Dru-0.247
Token Profile
Token ID13118
Feature activation+2.52e+00

Pos logit contributions
 contrace+1.594
 dstg+1.501
 Krishna+1.435
 Mississ+1.418
 Dru+1.415
Neg logit contributions
interstitial-0.883
apult-0.850
colored-0.822
anth-0.819
 Title-0.781
Token Blog
Token ID14001
Feature activation+1.12e+00

Pos logit contributions
interstitial+1.744
apult+1.715
anth+1.682
colored+1.661
 Title+1.633
Neg logit contributions
 contrace-2.236
 dstg-2.091
 Krishna-1.949
 Mississ-1.925
 Dru-1.917
Token Joined
Token ID16709
Feature activation+5.64e+00

Pos logit contributions
interstitial+0.816
apult+0.795
anth+0.783
colored+0.781
 Title+0.766
Neg logit contributions
 contrace-0.973
 dstg-0.884
 Krishna-0.826
 Mississ-0.819
 Dru-0.809
Token April
Token ID3035
Feature activation+1.02e+00

Pos logit contributions
 Title+3.287
interstitial+3.284
apult+3.223
anth+3.206
colored+3.199
Neg logit contributions
 contrace-5.511
 dstg-5.103
rists-4.785
 Krishna-4.630
 Mississ-4.579
Token 2012
Token ID2321
Feature activation+1.19e+00

Pos logit contributions
interstitial+0.769
apult+0.753
anth+0.739
colored+0.734
 Title+0.712
Neg logit contributions
 contrace-0.848
 dstg-0.787
 Krishna-0.734
 Mississ-0.724
 Dru-0.721
Token United
Token ID1578
Feature activation+6.97e-01

Pos logit contributions
interstitial+0.674
apult+0.654
anth+0.636
colored+0.631
 Title+0.604
Neg logit contributions
 contrace-1.220
 dstg-1.148
 Krishna-1.089
 Mississ-1.077
 Dru-1.074
Token States
Token ID1829
Feature activation+2.45e+00

Pos logit contributions
interstitial+0.438
apult+0.426
anth+0.416
colored+0.413
 Title+0.396
Neg logit contributions
 contrace-0.667
 dstg-0.625
 Krishna-0.592
 Mississ-0.585
 Dru-0.583
Token 5
Token ID642
Feature activation+2.06e-01

Pos logit contributions
interstitial+1.346
apult+1.314
anth+1.278
colored+1.267
 Title+1.236
Neg logit contributions
 contrace-2.529
 dstg-2.373
 Krishna-2.233
 Mississ-2.204
rists-2.202
Token2
Token ID17
Feature activation+2.69e+00

Pos logit contributions
interstitial+0.359
anth+0.345
apult+0.344
colored+0.343
 Title+0.325
Neg logit contributions
 contrace-0.570
 dstg-0.524
 Krishna-0.496
 Mississ-0.490
 Dru-0.490
Token-
Token ID12
Feature activation+1.70e+00

Pos logit contributions
 Title+1.802
interstitial+1.795
colored+1.792
apult+1.760
anth+1.746
Neg logit contributions
 contrace-2.448
 dstg-2.152
rists-2.049
 Mississ-2.003
 Krishna-1.999
Token1
Token ID16
Feature activation+7.66e-01

Pos logit contributions
interstitial+1.111
apult+1.071
anth+1.070
colored+1.068
 Title+1.025
Neg logit contributions
 contrace-1.599
 dstg-1.461
 Krishna-1.382
 Mississ-1.367
 Dru-1.358
Token/
Token ID14
Feature activation+2.66e+00

Pos logit contributions
interstitial+0.520
colored+0.510
apult+0.510
anth+0.506
 Title+0.497
Neg logit contributions
 contrace-0.690
 dstg-0.628
 Mississ-0.591
 Krishna-0.590
rists-0.585
Token2
Token ID17
Feature activation+3.01e+00

Pos logit contributions
interstitial+1.583
apult+1.538
colored+1.519
anth+1.514
 Title+1.449
Neg logit contributions
 contrace-2.619
 dstg-2.435
 Mississ-2.286
 Krishna-2.285
 Dru-2.269
Token"]
Token ID8973
Feature activation+5.53e+00

Pos logit contributions
interstitial+2.243
 Title+2.222
apult+2.221
colored+2.216
anth+2.186
Neg logit contributions
 contrace-2.455
 dstg-2.204
 Krishna-2.044
 Dru-2.038
 Mississ-2.025
Token [
Token ID685
Feature activation+3.45e+00

Pos logit contributions
 Title+2.835
interstitial+2.654
apult+2.650
colored+2.643
anth+2.598
Neg logit contributions
 contrace-6.110
 dstg-5.311
rists-5.070
 Krishna-5.029
 Mississ-5.022
TokenEC
Token ID2943
Feature activation-5.13e-01

Pos logit contributions
apult+1.186
interstitial+1.159
colored+1.154
anth+1.140
 Title+1.121
Neg logit contributions
 contrace-4.277
 dstg-4.011
 Krishna-3.825
rists-3.803
 Mississ-3.797
TokenO
Token ID46
Feature activation+2.98e+00

Pos logit contributions
 contrace+0.399
 dstg+0.369
 Krishna+0.344
 Mississ+0.339
 Dru+0.338
Neg logit contributions
interstitial-0.413
apult-0.405
anth-0.397
colored-0.395
 Title-0.382
Token "
Token ID366
Feature activation+2.59e+00

Pos logit contributions
 Title+2.085
interstitial+2.072
colored+2.058
apult+2.024
anth+2.010
Neg logit contributions
 contrace-2.680
 dstg-2.430
 Krishna-2.252
 Mississ-2.225
rists-2.189
TokenA
Token ID32
Feature activation+1.03e+00

Pos logit contributions
interstitial+1.720
apult+1.679
colored+1.638
anth+1.638
 Title+1.577
Neg logit contributions
 contrace-2.382
 dstg-2.224
 Krishna-2.100
 Mississ-2.073
 Dru-2.053
TokenK
Token ID42
Feature activation-1.50e+00

Pos logit contributions
 contrace+1.284
 dstg+1.201
 Krishna+1.135
 Mississ+1.120
 Dru+1.118
Neg logit contributions
interstitial-0.984
apult-0.957
anth-0.933
colored-0.929
 Title-0.895
Tokenier
Token ID959
Feature activation-1.29e+00

Pos logit contributions
 contrace+1.392
 dstg+1.309
 Krishna+1.236
 Mississ+1.222
 Dru+1.216
Neg logit contributions
interstitial-0.979
apult-0.946
colored-0.923
anth-0.920
 Title-0.885
Tokenan
Token ID272
Feature activation-3.33e-01

Pos logit contributions
 contrace+1.205
 dstg+1.126
 Krishna+1.067
 Mississ+1.052
 Dru+1.052
Neg logit contributions
interstitial-0.838
apult-0.810
anth-0.789
colored-0.787
 Title-0.755
Token Profile
Token ID13118
Feature activation+2.39e+00

Pos logit contributions
 contrace+0.347
 dstg+0.327
 Krishna+0.311
 Mississ+0.308
 Dru+0.307
Neg logit contributions
interstitial-0.181
apult-0.175
anth-0.169
colored-0.168
 Title-0.160
Token Blog
Token ID14001
Feature activation+1.23e+00

Pos logit contributions
interstitial+1.591
apult+1.567
anth+1.529
colored+1.515
 Title+1.481
Neg logit contributions
 contrace-2.179
 dstg-2.037
 Krishna-1.909
 Mississ-1.891
 Dru-1.878
Token Joined
Token ID16709
Feature activation+5.53e+00

Pos logit contributions
interstitial+0.907
apult+0.889
anth+0.872
colored+0.868
 Title+0.850
Neg logit contributions
 contrace-1.056
 dstg-0.966
 Krishna-0.902
 Mississ-0.893
 Dru-0.885
Token August
Token ID2932
Feature activation+1.12e+00

Pos logit contributions
interstitial+3.232
 Title+3.223
apult+3.169
anth+3.143
colored+3.138
Neg logit contributions
 contrace-5.386
 dstg-5.001
rists-4.690
 Krishna-4.532
 Mississ-4.483
Token 2011
Token ID2813
Feature activation+1.34e+00

Pos logit contributions
interstitial+0.836
apult+0.819
anth+0.806
colored+0.800
 Title+0.780
Neg logit contributions
 contrace-0.943
 dstg-0.875
 Krishna-0.813
 Mississ-0.801
 Dru-0.797
Token United
Token ID1578
Feature activation+1.11e+00

Pos logit contributions
interstitial+0.773
apult+0.751
anth+0.730
colored+0.725
 Title+0.693
Neg logit contributions
 contrace-1.344
 dstg-1.264
 Krishna-1.199
 Mississ-1.187
 Dru-1.182
Token States
Token ID1829
Feature activation+2.96e+00

Pos logit contributions
interstitial+0.685
apult+0.667
anth+0.651
colored+0.646
 Title+0.621
Neg logit contributions
 contrace-1.069
 dstg-1.003
 Krishna-0.948
 Mississ-0.937
 Dru-0.933
Token 6
Token ID718
Feature activation-3.98e-02

Pos logit contributions
interstitial+1.596
apult+1.561
anth+1.518
colored+1.507
 Title+1.484
Neg logit contributions
 contrace-3.087
 dstg-2.894
 Krishna-2.710
rists-2.689
 Mississ-2.674
Token
Token ID198
Feature activation+5.02e-02

Pos logit contributions
 contrace+0.167
 dstg+0.161
 Krishna+0.153
 Mississ+0.151
 Dru+0.151
Neg logit contributions
interstitial-0.097
apult-0.093
anth-0.090
colored-0.089
 Title-0.084
Tokenre
Token ID260
Feature activation+1.34e+00

Pos logit contributions
interstitial+0.035
apult+0.035
anth+0.034
colored+0.034
 Title+0.032
Neg logit contributions
 contrace-0.044
 dstg-0.041
 Krishna-0.039
 Mississ-0.038
 Dru-0.038
Tokeni
Token ID72
Feature activation-2.29e-01

Pos logit contributions
interstitial+0.915
apult+0.893
anth+0.874
colored+0.868
 Title+0.833
Neg logit contributions
 contrace-1.214
 dstg-1.133
 Krishna-1.068
 Mississ-1.056
 Dru-1.052
Token Profile
Token ID13118
Feature activation+2.98e+00

Pos logit contributions
 contrace+0.205
 dstg+0.191
 Krishna+0.181
 Mississ+0.178
 Dru+0.178
Neg logit contributions
interstitial-0.157
apult-0.153
anth-0.149
colored-0.149
 Title-0.143
Token Blog
Token ID14001
Feature activation+1.52e+00

Pos logit contributions
interstitial+2.048
apult+2.011
anth+1.977
colored+1.953
 Title+1.924
Neg logit contributions
 contrace-2.645
 dstg-2.468
 Krishna-2.305
 Mississ-2.275
 Dru-2.265
Token Joined
Token ID16709
Feature activation+5.52e+00

Pos logit contributions
interstitial+1.100
apult+1.070
anth+1.052
colored+1.051
 Title+1.033
Neg logit contributions
 contrace-1.330
 dstg-1.202
 Krishna-1.131
 Mississ-1.120
 Dru-1.107
Token October
Token ID3267
Feature activation+2.08e+00

Pos logit contributions
interstitial+3.235
 Title+3.217
apult+3.158
colored+3.145
anth+3.139
Neg logit contributions
 contrace-5.407
 dstg-4.978
rists-4.680
 Krishna-4.561
 Mississ-4.500
Token 2002
Token ID6244
Feature activation+5.54e-01

Pos logit contributions
interstitial+1.462
apult+1.440
anth+1.416
colored+1.402
 Title+1.380
Neg logit contributions
 contrace-1.831
 dstg-1.699
 Krishna-1.570
rists-1.553
 Mississ-1.552
Token United
Token ID1578
Feature activation+3.70e-01

Pos logit contributions
interstitial+0.318
apult+0.308
anth+0.300
colored+0.298
 Title+0.283
Neg logit contributions
 contrace-0.560
 dstg-0.528
 Krishna-0.502
 Mississ-0.497
 Dru-0.495
Token States
Token ID1829
Feature activation+2.06e+00

Pos logit contributions
interstitial+0.235
apult+0.228
anth+0.223
colored+0.221
 Title+0.212
Neg logit contributions
 contrace-0.353
 dstg-0.331
 Krishna-0.313
 Mississ-0.310
 Dru-0.309
Token 3
Token ID513
Feature activation+2.75e-01

Pos logit contributions
interstitial+1.138
apult+1.109
anth+1.077
colored+1.069
 Title+1.034
Neg logit contributions
 contrace-2.121
 dstg-1.993
 Krishna-1.882
 Mississ-1.860
 Dru-1.856
Token little
Token ID1310
Feature activation+3.42e-01

Pos logit contributions
interstitial+1.318
apult+1.269
anth+1.247
colored+1.243
 Title+1.201
Neg logit contributions
 contrace-1.682
 dstg-1.564
 Krishna-1.462
 Mississ-1.451
 Dru-1.436
Token as
Token ID355
Feature activation+2.54e+00

Pos logit contributions
interstitial+0.263
apult+0.257
anth+0.251
colored+0.250
 Title+0.239
Neg logit contributions
 contrace-0.275
 dstg-0.259
 Krishna-0.243
 Mississ-0.241
 Dru-0.240
Token $
Token ID720
Feature activation+2.97e+00

Pos logit contributions
interstitial+2.024
apult+1.981
anth+1.943
colored+1.932
 Title+1.872
Neg logit contributions
 contrace-2.008
 dstg-1.857
 Krishna-1.732
 Mississ-1.708
 Dru-1.701
Token2
Token ID17
Feature activation+2.50e+00

Pos logit contributions
interstitial+1.795
apult+1.741
anth+1.740
colored+1.696
 Title+1.637
Neg logit contributions
 contrace-2.934
 dstg-2.732
 Krishna-2.560
 Mississ-2.554
 Dru-2.525
Token a
Token ID257
Feature activation+2.60e+00

Pos logit contributions
interstitial+1.709
apult+1.663
anth+1.643
colored+1.626
 Title+1.567
Neg logit contributions
 contrace-2.274
 dstg-2.101
 Krishna-1.980
 Mississ-1.955
 Dru-1.946
Token month
Token ID1227
Feature activation+5.50e+00

Pos logit contributions
interstitial+1.312
apult+1.264
anth+1.234
colored+1.221
 Title+1.165
Neg logit contributions
 contrace-2.833
 dstg-2.665
 Krishna-2.535
 Mississ-2.507
 Dru-2.497
Token!
Token ID0
Feature activation+4.55e+00

Pos logit contributions
apult+3.215
interstitial+3.211
anth+3.177
colored+3.143
 Title+3.101
Neg logit contributions
 contrace-5.452
 dstg-4.917
rists-4.697
 Krishna-4.635
 Dru-4.582
Token
Token ID198
Feature activation+1.75e+00

Pos logit contributions
apult+2.026
interstitial+2.023
anth+1.977
 Title+1.974
colored+1.949
Neg logit contributions
 contrace-5.264
 dstg-4.732
 Krishna-4.515
rists-4.495
 Mississ-4.459
Token
Token ID198
Feature activation+1.53e+00

Pos logit contributions
interstitial+0.921
apult+0.897
anth+0.875
colored+0.867
 Title+0.831
Neg logit contributions
 contrace-1.866
 dstg-1.742
 Krishna-1.657
 Mississ-1.640
 Dru-1.633
TokenSupport
Token ID15514
Feature activation+2.72e+00

Pos logit contributions
interstitial+1.125
apult+1.098
anth+1.074
colored+1.071
 Title+1.031
Neg logit contributions
 contrace-1.303
 dstg-1.209
 Krishna-1.138
 Mississ-1.119
 Dru-1.119
Token Progressive
Token ID25852
Feature activation+1.87e+00

Pos logit contributions
interstitial+1.327
apult+1.279
anth+1.270
colored+1.251
 Title+1.226
Neg logit contributions
 contrace-3.011
 dstg-2.802
 Krishna-2.666
rists-2.628
 Dru-2.621
Token
Token ID198
Feature activation-7.15e-02

Pos logit contributions
interstitial+0.002
apult+0.002
anth+0.002
colored+0.002
 Title+0.002
Neg logit contributions
 contrace-0.004
 dstg-0.004
 Krishna-0.004
 Mississ-0.004
 Dru-0.004
TokenBig
Token ID12804
Feature activation+4.59e-01

Pos logit contributions
 contrace+0.063
 dstg+0.059
 Krishna+0.055
 Mississ+0.055
 Dru+0.055
Neg logit contributions
interstitial-0.050
apult-0.049
anth-0.048
colored-0.048
 Title-0.046
TokenFan
Token ID22480
Feature activation+3.32e-01

Pos logit contributions
interstitial+0.344
apult+0.338
anth+0.332
colored+0.329
 Title+0.320
Neg logit contributions
 contrace-0.384
 dstg-0.354
 Krishna-0.333
 Mississ-0.328
 Dru-0.326
Token Profile
Token ID13118
Feature activation+2.52e+00

Pos logit contributions
interstitial+0.200
apult+0.194
anth+0.190
colored+0.188
 Title+0.180
Neg logit contributions
 contrace-0.326
 dstg-0.306
 Krishna-0.290
 Mississ-0.287
 Dru-0.286
Token Blog
Token ID14001
Feature activation+8.01e-01

Pos logit contributions
interstitial+1.720
apult+1.692
anth+1.655
colored+1.639
 Title+1.603
Neg logit contributions
 contrace-2.256
 dstg-2.106
 Krishna-1.971
 Mississ-1.952
 Dru-1.940
Token Joined
Token ID16709
Feature activation+5.44e+00

Pos logit contributions
interstitial+0.602
apult+0.590
anth+0.578
colored+0.575
 Title+0.560
Neg logit contributions
 contrace-0.672
 dstg-0.618
 Krishna-0.578
 Mississ-0.572
 Dru-0.568
Token December
Token ID3426
Feature activation+1.47e+00

Pos logit contributions
interstitial+3.204
 Title+3.177
apult+3.142
anth+3.110
colored+3.106
Neg logit contributions
 contrace-5.298
 dstg-4.906
rists-4.600
 Krishna-4.465
 Mississ-4.411
Token 2010
Token ID3050
Feature activation+1.59e+00

Pos logit contributions
interstitial+1.092
apult+1.073
anth+1.056
colored+1.048
 Title+1.029
Neg logit contributions
 contrace-1.239
 dstg-1.145
 Krishna-1.060
 Mississ-1.047
rists-1.042
Token TL
Token ID24811
Feature activation-1.23e+00

Pos logit contributions
interstitial+0.894
apult+0.870
anth+0.845
colored+0.838
 Title+0.803
Neg logit contributions
 contrace-1.632
 dstg-1.536
 Krishna-1.455
 Mississ-1.440
 Dru-1.435
TokenAD
Token ID2885
Feature activation-7.65e-01

Pos logit contributions
 contrace+1.081
 dstg+1.005
 Krishna+0.954
 Mississ+0.944
 Dru+0.937
Neg logit contributions
interstitial-0.874
apult-0.850
anth-0.838
colored-0.830
 Title-0.790
TokenT
Token ID51
Feature activation+3.72e-01

Pos logit contributions
 contrace+0.731
 dstg+0.688
 Krishna+0.656
 Mississ+0.650
 Dru+0.645
Neg logit contributions
interstitial-0.470
apult-0.462
anth-0.455
colored-0.446
 Title-0.421
Token of
Token ID286
Feature activation-9.93e-01

Pos logit contributions
interstitial+0.573
apult+0.564
anth+0.554
colored+0.550
 Title+0.529
Neg logit contributions
 contrace-0.721
 dstg-0.672
 Krishna-0.629
 Mississ-0.624
 Dru-0.618
Token Dal
Token ID12348
Feature activation-5.35e-01

Pos logit contributions
 contrace+0.847
 dstg+0.789
 Krishna+0.743
 Mississ+0.733
 Dru+0.731
Neg logit contributions
interstitial-0.726
apult-0.709
anth-0.693
colored-0.689
 Title-0.663
TokenK
Token ID42
Feature activation-4.22e-01

Pos logit contributions
 contrace+0.474
 dstg+0.439
 Krishna+0.419
 Mississ+0.413
 Dru+0.411
Neg logit contributions
interstitial-0.372
apult-0.360
anth-0.352
colored-0.351
 Title-0.338
Token Profile
Token ID13118
Feature activation+7.72e-01

Pos logit contributions
 contrace+0.380
 dstg+0.354
 Krishna+0.334
 Mississ+0.330
 Dru+0.329
Neg logit contributions
interstitial-0.289
apult-0.282
anth-0.276
colored-0.274
 Title-0.264
Token Blog
Token ID14001
Feature activation+8.45e-01

Pos logit contributions
interstitial+0.532
apult+0.519
anth+0.508
colored+0.504
 Title+0.486
Neg logit contributions
 contrace-0.691
 dstg-0.646
 Krishna-0.608
 Mississ-0.601
 Dru-0.598
Token Joined
Token ID16709
Feature activation+5.43e+00

Pos logit contributions
interstitial+0.627
apult+0.613
anth+0.601
colored+0.599
 Title+0.586
Neg logit contributions
 contrace-0.720
 dstg-0.660
 Krishna-0.616
 Mississ-0.609
 Dru-0.605
Token June
Token ID2795
Feature activation+8.39e-01

Pos logit contributions
 Title+3.173
interstitial+3.173
apult+3.119
anth+3.094
colored+3.091
Neg logit contributions
 contrace-5.298
 dstg-4.905
rists-4.604
 Krishna-4.456
 Mississ-4.402
Token 2012
Token ID2321
Feature activation+1.80e+00

Pos logit contributions
interstitial+0.637
apult+0.625
anth+0.613
colored+0.609
 Title+0.592
Neg logit contributions
 contrace-0.692
 dstg-0.641
 Krishna-0.597
 Mississ-0.589
 Dru-0.585
Token Canada
Token ID3340
Feature activation+5.11e-01

Pos logit contributions
interstitial+1.028
apult+1.002
anth+0.974
colored+0.966
 Title+0.930
Neg logit contributions
 contrace-1.822
 dstg-1.713
 Krishna-1.618
 Mississ-1.601
 Dru-1.596
Token 16
Token ID1467
Feature activation-2.72e-01

Pos logit contributions
interstitial+0.283
apult+0.275
anth+0.267
colored+0.265
 Title+0.254
Neg logit contributions
 contrace-0.527
 dstg-0.496
 Krishna-0.470
 Mississ-0.465
 Dru-0.464
Token10
Token ID940
Feature activation+2.95e-01

Pos logit contributions
 contrace+0.246
 dstg+0.232
 Krishna+0.219
 Mississ+0.217
 Dru+0.216
Neg logit contributions
interstitial-0.184
apult-0.179
anth-0.175
colored-0.174
 Title-0.166
Tokenada
Token ID4763
Feature activation-7.85e-01

Pos logit contributions
 contrace+0.029
 dstg+0.027
 Krishna+0.025
 Mississ+0.025
 Dru+0.025
Neg logit contributions
interstitial-0.022
apult-0.022
anth-0.021
colored-0.021
 Title-0.020
Tokenver
Token ID332
Feature activation+4.55e-01

Pos logit contributions
 contrace+0.698
 dstg+0.651
 Krishna+0.614
 Mississ+0.606
 Dru+0.604
Neg logit contributions
interstitial-0.546
apult-0.532
anth-0.520
colored-0.517
 Title-0.497
TokenBB
Token ID15199
Feature activation-2.74e+00

Pos logit contributions
interstitial+0.286
apult+0.278
anth+0.272
colored+0.270
 Title+0.259
Neg logit contributions
 contrace-0.434
 dstg-0.407
 Krishna-0.385
 Mississ-0.381
 Dru-0.380
Token Profile
Token ID13118
Feature activation+2.28e+00

Pos logit contributions
 contrace+2.625
 dstg+2.466
 Krishna+2.353
 Mississ+2.312
 Dru+2.305
Neg logit contributions
interstitial-1.701
apult-1.639
anth-1.595
colored-1.590
 Title-1.512
Token Blog
Token ID14001
Feature activation+1.04e+00

Pos logit contributions
interstitial+1.523
apult+1.499
anth+1.465
colored+1.451
 Title+1.421
Neg logit contributions
 contrace-2.074
 dstg-1.939
 Krishna-1.814
 Mississ-1.797
 Dru-1.786
Token Joined
Token ID16709
Feature activation+5.34e+00

Pos logit contributions
interstitial+0.769
apult+0.753
anth+0.739
colored+0.737
 Title+0.721
Neg logit contributions
 contrace-0.893
 dstg-0.818
 Krishna-0.764
 Mississ-0.757
 Dru-0.750
Token June
Token ID2795
Feature activation+1.09e+00

Pos logit contributions
interstitial+3.142
 Title+3.125
apult+3.067
anth+3.045
colored+3.044
Neg logit contributions
 contrace-5.187
 dstg-4.822
rists-4.517
 Krishna-4.371
 Mississ-4.328
Token 2009
Token ID3717
Feature activation-1.44e-02

Pos logit contributions
interstitial+0.820
apult+0.806
anth+0.792
colored+0.786
 Title+0.769
Neg logit contributions
 contrace-0.905
 dstg-0.838
 Krishna-0.777
 Mississ-0.765
rists-0.761
Token Germany
Token ID4486
Feature activation-2.14e-01

Pos logit contributions
 contrace+0.015
 dstg+0.014
 Krishna+0.013
 Mississ+0.013
 Dru+0.013
Neg logit contributions
interstitial-0.008
apult-0.008
anth-0.008
colored-0.008
 Title-0.007
Token 247
Token ID30179
Feature activation-2.09e+00

Pos logit contributions
 contrace+0.216
 dstg+0.204
 Krishna+0.195
 Mississ+0.193
 Dru+0.192
Neg logit contributions
interstitial-0.124
apult-0.119
anth-0.116
colored-0.115
 Title-0.108
Token34
Token ID2682
Feature activation-4.16e-01

Pos logit contributions
 contrace+1.763
 dstg+1.671
 Krishna+1.581
 Mississ+1.560
 Dru+1.555
Neg logit contributions
interstitial-1.528
apult-1.485
colored-1.448
anth-1.446
 Title-1.363
Token.
Token ID13
Feature activation+4.42e+00

Pos logit contributions
interstitial+0.812
apult+0.801
anth+0.791
colored+0.782
 Title+0.760
Neg logit contributions
 contrace-0.978
 dstg-0.873
 Krishna-0.825
 Mississ-0.816
 Dru-0.808
Token00
Token ID405
Feature activation+4.28e+00

Pos logit contributions
interstitial+2.692
apult+2.614
anth+2.586
colored+2.546
 Title+2.449
Neg logit contributions
 contrace-4.322
 dstg-3.997
 Krishna-3.801
 Mississ-3.762
 Dru-3.745
Token96
Token ID4846
Feature activation+4.19e+00

Pos logit contributions
interstitial+2.757
apult+2.713
anth+2.690
colored+2.662
 Title+2.609
Neg logit contributions
 contrace-4.055
 dstg-3.691
 Krishna-3.444
 Mississ-3.421
rists-3.402
Token275
Token ID23195
Feature activation+5.79e+00

Pos logit contributions
interstitial+2.773
apult+2.720
anth+2.692
colored+2.656
 Title+2.600
Neg logit contributions
 contrace-3.888
 dstg-3.537
 Krishna-3.310
 Mississ-3.277
 Dru-3.267
Token.
Token ID13
Feature activation+6.31e+00

Pos logit contributions
 Title+3.699
interstitial+3.566
colored+3.498
apult+3.489
anth+3.461
Neg logit contributions
 contrace-5.582
 dstg-4.968
rists-4.758
 Dru-4.600
 Mississ-4.575
Tokeng
Token ID70
Feature activation+5.26e+00

Pos logit contributions
interstitial+3.695
apult+3.651
colored+3.637
anth+3.632
 Title+3.527
Neg logit contributions
 contrace-6.250
 dstg-5.689
 Krishna-5.477
 Dru-5.459
 Mississ-5.338
Token001
Token ID8298
Feature activation+4.69e+00

Pos logit contributions
interstitial+2.315
apult+2.305
 Title+2.254
anth+2.249
colored+2.184
Neg logit contributions
 contrace-6.029
 dstg-5.492
 Krishna-5.380
 Dru-5.285
 Mississ-5.241
Token Pre
Token ID3771
Feature activation+6.44e-01

Pos logit contributions
interstitial+2.847
apult+2.842
 Title+2.773
colored+2.756
anth+2.743
Neg logit contributions
 contrace-4.511
 dstg-4.134
rists-3.881
 Krishna-3.844
 Mississ-3.808
Token-
Token ID12
Feature activation+4.14e-01

Pos logit contributions
interstitial+0.469
apult+0.458
anth+0.448
colored+0.447
 Title+0.430
Neg logit contributions
 contrace-0.553
 dstg-0.515
 Krishna-0.482
 Mississ-0.477
 Dru-0.474
Tokentraining
Token ID34409
Feature activation-2.38e-01

Pos logit contributions
interstitial+0.245
apult+0.238
anth+0.232
colored+0.230
 Title+0.220
Neg logit contributions
 contrace-0.411
 dstg-0.386
 Krishna-0.366
 Mississ-0.362
 Dru-0.361
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
 contrace+0.213
 dstg+0.199
 Krishna+0.187
 Mississ+0.185
 Dru+0.184
Neg logit contributions
interstitial-0.164
apult-0.160
anth-0.156
colored-0.155
 Title-0.150
Token as
Token ID355
Feature activation+6.41e-02

Pos logit contributions
 contrace+0.913
 dstg+0.848
 Krishna+0.795
 Mississ+0.784
 Dru+0.782
Neg logit contributions
interstitial-0.856
apult-0.836
anth-0.818
colored-0.813
 Title-0.785
Token well
Token ID880
Feature activation+4.96e-01

Pos logit contributions
interstitial+0.047
apult+0.046
anth+0.045
colored+0.045
 Title+0.043
Neg logit contributions
 contrace-0.055
 dstg-0.051
 Krishna-0.048
 Mississ-0.047
 Dru-0.047
Token.
Token ID13
Feature activation-7.98e-01

Pos logit contributions
interstitial+0.372
apult+0.364
anth+0.357
colored+0.355
 Title+0.343
Neg logit contributions
 contrace-0.414
 dstg-0.384
 Krishna-0.360
 Mississ-0.356
 Dru-0.354
Token<|endoftext|>
Token ID50256
Feature activation+5.03e-01

Pos logit contributions
 contrace+0.755
 dstg+0.715
 Krishna+0.680
 Dru+0.671
 Mississ+0.670
Neg logit contributions
interstitial-0.510
apult-0.490
anth-0.478
colored-0.476
 Title-0.448
TokenHA
Token ID7801
Feature activation-2.40e+00

Pos logit contributions
interstitial+0.353
apult+0.344
anth+0.338
colored+0.336
 Title+0.323
Neg logit contributions
 contrace-0.445
 dstg-0.414
 Krishna-0.390
 Mississ-0.385
 Dru-0.384
TokenV
Token ID53
Feature activation+5.25e+00

Pos logit contributions
 contrace+2.328
 dstg+2.202
 Krishna+2.107
 Mississ+2.065
 Dru+2.065
Neg logit contributions
interstitial-1.464
apult-1.411
anth-1.375
colored-1.366
 Title-1.287
TokenANA
Token ID31574
Feature activation+8.62e-01

Pos logit contributions
interstitial+3.154
apult+3.094
anth+3.054
colored+3.032
 Title+2.958
Neg logit contributions
 contrace-5.096
 dstg-4.752
 Mississ-4.394
 Dru-4.349
 Krishna-4.317
Token (
Token ID357
Feature activation+1.17e+00

Pos logit contributions
interstitial+0.670
apult+0.657
anth+0.645
colored+0.642
 Title+0.623
Neg logit contributions
 contrace-0.694
 dstg-0.642
 Krishna-0.599
 Mississ-0.591
 Dru-0.587
TokenReuters
Token ID12637
Feature activation+9.76e-01

Pos logit contributions
interstitial+0.873
apult+0.853
anth+0.839
colored+0.833
 Title+0.805
Neg logit contributions
 contrace-0.986
 dstg-0.914
 Krishna-0.854
 Mississ-0.844
 Dru-0.839
Token)
Token ID8
Feature activation+2.41e+00

Pos logit contributions
interstitial+0.784
apult+0.772
anth+0.759
colored+0.752
 Title+0.735
Neg logit contributions
 contrace-0.763
 dstg-0.696
 Krishna-0.650
 Mississ-0.640
 Dru-0.636
Token -
Token ID532
Feature activation+2.96e+00

Pos logit contributions
interstitial+1.988
apult+1.969
anth+1.951
colored+1.929
 Title+1.903
Neg logit contributions
 contrace-1.872
 dstg-1.638
 Krishna-1.508
 Mississ-1.494
rists-1.490
Token image
Token ID2939
Feature activation+2.44e+00

Pos logit contributions
interstitial+1.058
apult+1.031
anth+1.014
colored+1.008
 Title+0.977
Neg logit contributions
 contrace-1.295
 dstg-1.195
 Krishna-1.123
 Mississ-1.109
 Dru-1.104
Token
Token ID198
Feature activation+2.77e+00

Pos logit contributions
interstitial+1.337
apult+1.295
anth+1.259
colored+1.248
 Title+1.185
Neg logit contributions
 contrace-2.524
 dstg-2.386
 Krishna-2.269
 Mississ-2.245
 Dru-2.238
Token
Token ID198
Feature activation+1.96e+00

Pos logit contributions
interstitial+1.384
apult+1.362
anth+1.336
colored+1.321
 Title+1.279
Neg logit contributions
 contrace-3.031
 dstg-2.792
 Krishna-2.657
 Mississ-2.631
 Dru-2.616
Tokenlarg
Token ID15521
Feature activation+1.97e+00

Pos logit contributions
interstitial+0.799
apult+0.766
anth+0.739
colored+0.731
 Title+0.678
Neg logit contributions
 contrace-2.319
 dstg-2.199
 Krishna-2.108
 Mississ-2.088
 Dru-2.084
Tokener
Token ID263
Feature activation+3.51e+00

Pos logit contributions
interstitial+1.110
apult+1.085
anth+1.063
colored+1.057
 Title+1.014
Neg logit contributions
 contrace-2.032
 dstg-1.890
 Krishna-1.783
 Mississ-1.766
 Dru-1.760
Token image
Token ID2939
Feature activation+5.24e+00

Pos logit contributions
interstitial+2.523
apult+2.463
anth+2.413
colored+2.405
 Title+2.331
Neg logit contributions
 contrace-3.053
 dstg-2.821
 Krishna-2.647
 Mississ-2.620
 Dru-2.606
Token T
Token ID309
Feature activation+1.91e+00

Pos logit contributions
interstitial+2.429
apult+2.393
 Title+2.309
colored+2.232
anth+2.216
Neg logit contributions
 contrace-5.923
 dstg-5.553
 Krishna-5.265
rists-5.225
 Mississ-5.205
TokenIFF
Token ID29267
Feature activation+7.06e-01

Pos logit contributions
interstitial+1.415
apult+1.383
anth+1.356
colored+1.348
 Title+1.306
Neg logit contributions
 contrace-1.608
 dstg-1.493
 Krishna-1.403
 Mississ-1.384
 Dru-1.379
Token original
Token ID2656
Feature activation+3.03e+00

Pos logit contributions
interstitial+0.438
apult+0.427
anth+0.416
colored+0.413
 Title+0.396
Neg logit contributions
 contrace-0.680
 dstg-0.638
 Krishna-0.604
 Mississ-0.598
 Dru-0.595
Token image
Token ID2939
Feature activation+4.08e+00

Pos logit contributions
interstitial+2.160
apult+2.106
colored+2.060
anth+2.060
 Title+1.995
Neg logit contributions
 contrace-2.654
 dstg-2.447
 Krishna-2.301
 Mississ-2.279
 Dru-2.269
Token Download
Token ID10472
Feature activation+1.56e-01

Pos logit contributions
apult+1.950
interstitial+1.926
 Title+1.835
colored+1.835
anth+1.778
Neg logit contributions
 contrace-4.559
 dstg-4.233
 Krishna-4.016
 Mississ-3.993
rists-3.992
Tokenrock
Token ID10823
Feature activation+1.62e-01

Pos logit contributions
 contrace+1.138
 dstg+1.056
 Krishna+0.988
 Mississ+0.978
 Dru+0.972
Neg logit contributions
interstitial-1.102
apult-1.072
anth-1.047
colored-1.046
 Title-1.011
Token -
Token ID532
Feature activation+1.05e+00

Pos logit contributions
interstitial+0.135
apult+0.132
anth+0.130
colored+0.129
 Title+0.125
Neg logit contributions
 contrace-0.122
 dstg-0.113
 Krishna-0.105
 Mississ-0.103
 Dru-0.103
Token favorite
Token ID4004
Feature activation+3.84e+00

Pos logit contributions
interstitial+0.721
apult+0.703
anth+0.688
colored+0.683
 Title+0.659
Neg logit contributions
 contrace-0.943
 dstg-0.881
 Krishna-0.830
 Mississ-0.820
 Dru-0.816
Token favorite
Token ID4004
Feature activation+4.31e+00

Pos logit contributions
interstitial+2.390
apult+2.327
anth+2.321
colored+2.319
 Title+2.273
Neg logit contributions
 contrace-3.652
 dstg-3.413
 Krishna-3.200
 Mississ-3.157
 Dru-3.137
Token favorite
Token ID4004
Feature activation+4.96e+00

Pos logit contributions
interstitial+2.692
apult+2.625
anth+2.615
colored+2.614
 Title+2.562
Neg logit contributions
 contrace-4.068
 dstg-3.803
 Krishna-3.575
 Mississ-3.526
 Dru-3.505
Token favorite
Token ID4004
Feature activation+5.21e+00

Pos logit contributions
interstitial+3.203
apult+3.120
colored+3.113
anth+3.106
 Title+3.050
Neg logit contributions
 contrace-4.542
 dstg-4.240
 Krishna-4.001
 Mississ-3.945
 Dru-3.918
Token -
Token ID532
Feature activation+1.91e+00

Pos logit contributions
interstitial+3.731
apult+3.641
colored+3.638
anth+3.628
 Title+3.572
Neg logit contributions
 contrace-4.401
 dstg-4.079
 Krishna-3.839
 Mississ-3.772
 Dru-3.745
Token December
Token ID3426
Feature activation+2.14e+00

Pos logit contributions
interstitial+1.302
apult+1.272
anth+1.252
colored+1.241
 Title+1.206
Neg logit contributions
 contrace-1.725
 dstg-1.609
 Krishna-1.505
 Mississ-1.486
 Dru-1.478
Token 13
Token ID1511
Feature activation+2.86e-01

Pos logit contributions
interstitial+1.189
apult+1.161
anth+1.146
colored+1.132
 Title+1.106
Neg logit contributions
 contrace-2.205
 dstg-2.049
 Krishna-1.930
 Mississ-1.910
rists-1.905
Token,
Token ID11
Feature activation-1.31e+00

Pos logit contributions
interstitial+0.215
apult+0.210
anth+0.203
colored+0.202
 Title+0.194
Neg logit contributions
 contrace-0.235
 dstg-0.223
 Krishna-0.209
 Mississ-0.207
 Dru-0.206
Token 2010
Token ID3050
Feature activation+1.53e+00

Pos logit contributions
 contrace+1.043
 dstg+0.971
 Krishna+0.911
 Mississ+0.902
 Dru+0.900
Neg logit contributions
interstitial-1.021
apult-0.995
anth-0.967
colored-0.963
 Title-0.924
Token the
Token ID262
Feature activation-2.85e-01

Pos logit contributions
 contrace+0.642
 dstg+0.596
 Krishna+0.561
 Dru+0.553
 Mississ+0.553
Neg logit contributions
interstitial-0.567
apult-0.552
anth-0.538
colored-0.534
 Title-0.515
Token Clojure
Token ID43848
Feature activation+2.59e+00

Pos logit contributions
 contrace+0.246
 dstg+0.230
 Krishna+0.216
 Mississ+0.213
 Dru+0.212
Neg logit contributions
interstitial-0.205
apult-0.200
anth-0.196
colored-0.195
 Title-0.188
Token subset
Token ID24637
Feature activation-1.57e+00

Pos logit contributions
interstitial+1.823
apult+1.809
anth+1.776
colored+1.762
 Title+1.726
Neg logit contributions
 contrace-2.237
 dstg-2.083
 Krishna-1.959
 Mississ-1.941
 Dru-1.919
Token of
Token ID286
Feature activation-1.97e-01

Pos logit contributions
 contrace+1.330
 dstg+1.244
 Krishna+1.168
 Dru+1.152
 Mississ+1.145
Neg logit contributions
interstitial-1.153
apult-1.119
anth-1.090
colored-1.081
 Title-1.041
Token the
Token ID262
Feature activation-7.93e-02

Pos logit contributions
 contrace+0.162
 dstg+0.150
 Krishna+0.141
 Mississ+0.139
 Dru+0.138
Neg logit contributions
interstitial-0.150
apult-0.147
anth-0.144
colored-0.143
 Title-0.138
Token GitHub
Token ID21722
Feature activation+5.21e+00

Pos logit contributions
 contrace+0.072
 dstg+0.068
 Krishna+0.064
 Mississ+0.063
 Dru+0.063
Neg logit contributions
interstitial-0.053
apult-0.052
anth-0.051
colored-0.050
 Title-0.049
Token dataset
Token ID27039
Feature activation-1.90e-01

Pos logit contributions
anth+3.144
apult+3.136
colored+3.111
interstitial+3.101
 Title+3.062
Neg logit contributions
 contrace-4.839
 dstg-4.538
 Mississ-4.258
 Krishna-4.254
rists-4.243
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
 contrace+0.156
 dstg+0.145
 Krishna+0.136
 Mississ+0.134
 Dru+0.133
Neg logit contributions
interstitial-0.145
apult-0.142
anth-0.139
colored-0.138
 Title-0.133
Token I
Token ID314
Feature activation+1.05e+00

Pos logit contributions
interstitial+0.394
apult+0.383
anth+0.374
colored+0.371
 Title+0.355
Neg logit contributions
 contrace-0.635
 dstg-0.597
 Krishna-0.565
 Mississ-0.559
 Dru-0.557
Token did
Token ID750
Feature activation+1.40e+00

Pos logit contributions
interstitial+0.755
apult+0.740
anth+0.725
colored+0.721
 Title+0.696
Neg logit contributions
 contrace-0.901
 dstg-0.840
 Krishna-0.788
 Mississ-0.779
 Dru-0.774
Token this
Token ID428
Feature activation-6.81e-01

Pos logit contributions
interstitial+0.997
apult+0.973
anth+0.952
colored+0.946
 Title+0.913
Neg logit contributions
 contrace-1.220
 dstg-1.137
 Krishna-1.069
 Mississ-1.056
 Dru-1.052
Token
Token ID198
Feature activation-5.42e-01

Pos logit contributions
 contrace+1.166
 dstg+1.139
 Krishna+1.085
 Dru+1.073
 Mississ+1.071
Neg logit contributions
interstitial-0.732
apult-0.699
anth-0.668
colored-0.665
 Title-0.623
TokenDark
Token ID17367
Feature activation-2.19e-01

Pos logit contributions
 contrace+0.477
 dstg+0.445
 Krishna+0.419
 Mississ+0.414
 Dru+0.413
Neg logit contributions
interstitial-0.381
apult-0.372
anth-0.363
colored-0.360
 Title-0.349
Tokenhorse
Token ID30527
Feature activation-3.99e-01

Pos logit contributions
 contrace+0.190
 dstg+0.177
 Krishna+0.166
 Mississ+0.164
 Dru+0.164
Neg logit contributions
interstitial-0.158
apult-0.154
anth-0.151
colored-0.150
 Title-0.145
Token Profile
Token ID13118
Feature activation+1.59e+00

Pos logit contributions
 contrace+0.379
 dstg+0.355
 Krishna+0.336
 Mississ+0.332
 Dru+0.332
Neg logit contributions
interstitial-0.253
apult-0.246
anth-0.240
colored-0.238
 Title-0.228
Token Blog
Token ID14001
Feature activation+1.01e+00

Pos logit contributions
interstitial+1.109
apult+1.087
anth+1.063
colored+1.054
 Title+1.024
Neg logit contributions
 contrace-1.406
 dstg-1.312
 Krishna-1.231
 Mississ-1.216
 Dru-1.210
Token Joined
Token ID16709
Feature activation+5.19e+00

Pos logit contributions
interstitial+0.748
apult+0.733
anth+0.720
colored+0.716
 Title+0.700
Neg logit contributions
 contrace-0.865
 dstg-0.791
 Krishna-0.739
 Mississ-0.732
 Dru-0.725
Token December
Token ID3426
Feature activation+1.14e+00

Pos logit contributions
interstitial+3.070
 Title+3.052
apult+3.018
anth+2.991
colored+2.984
Neg logit contributions
 contrace-5.037
 dstg-4.665
rists-4.368
 Krishna-4.244
 Mississ-4.200
Token 2011
Token ID2813
Feature activation+1.49e+00

Pos logit contributions
interstitial+0.839
apult+0.823
anth+0.808
colored+0.802
 Title+0.783
Neg logit contributions
 contrace-0.963
 dstg-0.893
 Krishna-0.830
 Mississ-0.820
 Dru-0.814
Token United
Token ID1578
Feature activation+7.09e-01

Pos logit contributions
interstitial+0.855
apult+0.833
anth+0.810
colored+0.803
 Title+0.774
Neg logit contributions
 contrace-1.506
 dstg-1.416
 Krishna-1.337
 Mississ-1.322
 Dru-1.318
Token States
Token ID1829
Feature activation+2.41e+00

Pos logit contributions
interstitial+0.443
apult+0.432
anth+0.421
colored+0.418
 Title+0.401
Neg logit contributions
 contrace-0.680
 dstg-0.638
 Krishna-0.604
 Mississ-0.597
 Dru-0.595
Token 228
Token ID29041
Feature activation-1.80e+00

Pos logit contributions
interstitial+1.318
apult+1.287
anth+1.252
colored+1.242
 Title+1.213
Neg logit contributions
 contrace-2.497
 dstg-2.344
 Krishna-2.204
rists-2.176
 Mississ-2.176
Token make
Token ID787
Feature activation-5.09e-01

Pos logit contributions
 contrace+0.632
 dstg+0.588
 Krishna+0.553
 Mississ+0.546
 Dru+0.544
Neg logit contributions
interstitial-0.527
apult-0.514
anth-0.502
colored-0.500
 Title-0.482
Token?
Token ID30
Feature activation-1.50e-01

Pos logit contributions
 contrace+0.430
 dstg+0.401
 Krishna+0.378
 Mississ+0.373
 Dru+0.370
Neg logit contributions
interstitial-0.377
apult-0.366
anth-0.358
colored-0.356
 Title-0.343
Token The
Token ID383
Feature activation-6.42e-01

Pos logit contributions
 contrace+0.141
 dstg+0.132
 Krishna+0.125
 Mississ+0.124
 Dru+0.123
Neg logit contributions
interstitial-0.097
apult-0.094
anth-0.092
colored-0.092
 Title-0.088
Token same
Token ID976
Feature activation-5.22e-01

Pos logit contributions
 contrace+0.534
 dstg+0.497
 Krishna+0.465
 Mississ+0.457
 Dru+0.455
Neg logit contributions
interstitial-0.482
apult-0.473
anth-0.464
colored-0.460
 Title-0.446
Token arguments
Token ID7159
Feature activation-2.00e-01

Pos logit contributions
 contrace+0.418
 dstg+0.390
 Krishna+0.362
 Mississ+0.354
 Dru+0.354
Neg logit contributions
interstitial-0.408
apult-0.400
anth-0.393
colored-0.390
 Title-0.380
Token Ign
Token ID16583
Feature activation-6.82e+00

Pos logit contributions
 contrace+0.170
 dstg+0.158
 Krishna+0.148
 Mississ+0.146
 Dru+0.145
Neg logit contributions
interstitial-0.147
apult-0.144
anth-0.141
colored-0.140
 Title-0.136
Tokenat
Token ID265
Feature activation-1.00e+00

Pos logit contributions
 dstg+5.194
 contrace+5.071
 Dru+4.906
 Krishna+4.839
 Mississ+4.806
Neg logit contributions
interstitial-5.109
apult-4.791
colored-4.445
 Title-4.394
-4.389
Tokenie
Token ID494
Feature activation-1.69e+00

Pos logit contributions
 contrace+1.012
 dstg+0.972
 Krishna+0.923
 Dru+0.916
 Mississ+0.913
Neg logit contributions
interstitial-0.561
apult-0.539
anth-0.518
colored-0.511
 Title-0.491
Tokenff
Token ID487
Feature activation-2.06e+00

Pos logit contributions
 contrace+1.310
 dstg+1.257
 Krishna+1.171
 Dru+1.160
 Mississ+1.153
Neg logit contributions
interstitial-1.341
apult-1.298
anth-1.259
colored-1.250
 Title-1.213
Token is
Token ID318
Feature activation-1.53e+00

Pos logit contributions
 contrace+1.723
 dstg+1.595
 Krishna+1.500
 Mississ+1.482
 Dru+1.475
Neg logit contributions
interstitial-1.542
apult-1.500
anth-1.468
colored-1.459
 Title-1.409
Token making
Token ID1642
Feature activation-1.19e+00

Pos logit contributions
 contrace+1.259
 dstg+1.167
 Krishna+1.095
 Mississ+1.081
 Dru+1.076
Neg logit contributions
interstitial-1.160
apult-1.133
anth-1.111
colored-1.104
 Title-1.066
Tokenphone
Token ID4862
Feature activation-9.48e-01

Pos logit contributions
 contrace+1.867
 dstg+1.704
 Krishna+1.562
 Mississ+1.541
 Dru+1.534
Neg logit contributions
interstitial-2.613
apult-2.577
anth-2.525
colored-2.511
 Title-2.451
Token in
Token ID287
Feature activation+1.23e-02

Pos logit contributions
 contrace+0.768
 dstg+0.710
 Krishna+0.665
 Mississ+0.656
 Dru+0.652
Neg logit contributions
interstitial-0.735
apult-0.719
anth-0.705
colored-0.702
 Title-0.682
Token phones
Token ID9512
Feature activation+2.20e+00

Pos logit contributions
interstitial+0.014
apult+0.014
anth+0.013
colored+0.013
 Title+0.013
Neg logit contributions
 contrace-0.006
 dstg-0.005
 Krishna-0.004
 Mississ-0.004
 Dru-0.004
Token">
Token ID5320
Feature activation-2.36e+00

Pos logit contributions
interstitial+1.682
apult+1.656
anth+1.627
colored+1.615
 Title+1.577
Neg logit contributions
 contrace-1.790
 dstg-1.658
 Krishna-1.558
 Mississ-1.531
 Dru-1.516
Token <
Token ID1279
Feature activation-3.32e-01

Pos logit contributions
 contrace+2.066
 dstg+1.932
 Krishna+1.813
 Mississ+1.799
 Dru+1.797
Neg logit contributions
interstitial-1.653
apult-1.625
anth-1.582
colored-1.567
 Title-1.506
Tokenspan
Token ID12626
Feature activation-6.58e+00

Pos logit contributions
 contrace+0.330
 dstg+0.311
 Krishna+0.295
 Mississ+0.292
 Dru+0.291
Neg logit contributions
interstitial-0.195
apult-0.190
anth-0.184
colored-0.183
 Title-0.175
Token ng
Token ID23370
Feature activation-3.67e+00

Pos logit contributions
 contrace+4.768
 dstg+4.609
 Dru+4.297
 Krishna+4.230
 Mississ+4.171
Neg logit contributions
interstitial-5.332
apult-5.162
anth-5.010
colored-4.925
-4.697
Token-
Token ID12
Feature activation-1.29e+00

Pos logit contributions
 contrace+2.710
 dstg+2.520
 Krishna+2.341
 Mississ+2.325
 Dru+2.318
Neg logit contributions
interstitial-3.031
apult-2.979
anth-2.907
colored-2.882
 Title-2.775
Tokenbind
Token ID21653
Feature activation-4.13e+00

Pos logit contributions
 contrace+1.261
 dstg+1.192
 Krishna+1.126
 Mississ+1.117
 Dru+1.110
Neg logit contributions
interstitial-0.768
apult-0.756
anth-0.728
colored-0.718
 Title-0.693
Token="
Token ID2625
Feature activation-3.84e+00

Pos logit contributions
 contrace+2.953
 dstg+2.756
 Krishna+2.536
 Mississ+2.530
 Dru+2.518
Neg logit contributions
interstitial-3.493
apult-3.408
anth-3.329
colored-3.286
 Title-3.141
Tokenphone
Token ID4862
Feature activation-4.66e-01

Pos logit contributions
 contrace+3.126
 dstg+2.914
 Krishna+2.717
 Mississ+2.702
 Dru+2.690
Neg logit contributions
interstitial-2.864
apult-2.840
anth-2.753
colored-2.725
 Title-2.652
Token <
Token ID1279
Feature activation+1.51e+00

Pos logit contributions
interstitial+1.388
apult+1.364
anth+1.334
colored+1.333
 Title+1.299
Neg logit contributions
 contrace-1.254
 dstg-1.142
 Krishna-1.063
 Mississ-1.041
 Dru-1.035
Token T
Token ID309
Feature activation+1.91e+00

Pos logit contributions
interstitial+0.792
apult+0.777
colored+0.750
anth+0.744
 Title+0.733
Neg logit contributions
 contrace-1.584
 dstg-1.492
 Krishna-1.414
 Mississ-1.397
rists-1.389
Token >
Token ID1875
Feature activation+7.76e-01

Pos logit contributions
interstitial+1.541
apult+1.516
anth+1.486
colored+1.483
 Title+1.453
Neg logit contributions
 contrace-1.480
 dstg-1.352
 Krishna-1.260
 Mississ-1.243
 Dru-1.231
Token {
Token ID1391
Feature activation+1.71e+00

Pos logit contributions
interstitial+0.558
apult+0.546
anth+0.534
colored+0.534
 Title+0.523
Neg logit contributions
 contrace-0.672
 dstg-0.618
 Krishna-0.575
 Mississ-0.570
 Dru-0.564
Token pub
Token ID2240
Feature activation+7.81e-01

Pos logit contributions
interstitial+1.135
apult+1.115
colored+1.094
 Title+1.078
anth+1.076
Neg logit contributions
 contrace-1.552
 dstg-1.453
 Krishna-1.364
 Mississ-1.353
 Dru-1.335
Token fn
Token ID24714
Feature activation-6.22e+00

Pos logit contributions
interstitial+0.491
apult+0.481
anth+0.468
colored+0.466
 Title+0.451
Neg logit contributions
 contrace-0.743
 dstg-0.697
 Krishna-0.659
 Mississ-0.651
 Dru-0.647
Token new
Token ID649
Feature activation+3.97e-02

Pos logit contributions
 contrace+5.074
 dstg+4.648
 Krishna+4.419
 Mississ+4.390
 Dru+4.370
Neg logit contributions
interstitial-4.659
anth-4.495
apult-4.494
colored-4.392
-4.163
Token (
Token ID357
Feature activation-7.42e-02

Pos logit contributions
interstitial+0.031
apult+0.030
anth+0.029
colored+0.029
 Title+0.028
Neg logit contributions
 contrace-0.033
 dstg-0.030
 Krishna-0.028
 Mississ-0.028
 Dru-0.028
Token t
Token ID256
Feature activation+3.54e-01

Pos logit contributions
 contrace+0.063
 dstg+0.058
 Krishna+0.055
 Mississ+0.054
 Dru+0.054
Neg logit contributions
interstitial-0.055
apult-0.054
anth-0.053
colored-0.053
 Title-0.051
Token :
Token ID1058
Feature activation-1.28e+00

Pos logit contributions
interstitial+0.238
apult+0.234
anth+0.229
colored+0.227
 Title+0.220
Neg logit contributions
 contrace-0.321
 dstg-0.299
 Krishna-0.283
 Mississ-0.279
 Dru-0.277
Token T
Token ID309
Feature activation-8.44e-02

Pos logit contributions
 contrace+1.234
 dstg+1.155
 Krishna+1.095
 Mississ+1.087
 Dru+1.085
Neg logit contributions
interstitial-0.807
apult-0.779
anth-0.762
colored-0.754
 Title-0.716
Token null
Token ID9242
Feature activation+6.18e-01

Pos logit contributions
 contrace+0.122
 dstg+0.114
 Krishna+0.106
 Mississ+0.105
 Dru+0.104
Neg logit contributions
interstitial-0.111
apult-0.109
anth-0.107
colored-0.107
 Title-0.104
Token atomic
Token ID17226
Feature activation-7.35e-02

Pos logit contributions
interstitial+0.417
apult+0.408
colored+0.400
anth+0.399
 Title+0.384
Neg logit contributions
 contrace-0.561
 dstg-0.524
 Krishna-0.494
 Mississ-0.489
 Dru-0.486
Token pointer
Token ID17562
Feature activation+1.59e-01

Pos logit contributions
 contrace+0.063
 dstg+0.058
 Krishna+0.055
 Mississ+0.054
 Dru+0.054
Neg logit contributions
interstitial-0.054
apult-0.053
anth-0.051
colored-0.051
 Title-0.050
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
interstitial+0.116
apult+0.113
anth+0.111
colored+0.110
 Title+0.107
Neg logit contributions
 contrace-0.137
 dstg-0.127
 Krishna-0.119
 Mississ-0.118
 Dru-0.117
Token pub
Token ID2240
Feature activation+5.97e-01

Pos logit contributions
interstitial+0.746
apult+0.731
anth+0.714
colored+0.714
 Title+0.697
Neg logit contributions
 contrace-0.971
 dstg-0.909
 Krishna-0.854
 Mississ-0.843
 Dru-0.836
Token fn
Token ID24714
Feature activation-6.12e+00

Pos logit contributions
interstitial+0.385
apult+0.377
anth+0.367
colored+0.365
 Title+0.353
Neg logit contributions
 contrace-0.559
 dstg-0.524
 Krishna-0.495
 Mississ-0.490
 Dru-0.487
Token null
Token ID9242
Feature activation+3.38e-03

Pos logit contributions
 contrace+4.720
 dstg+4.273
 Krishna+4.077
 Dru+4.024
 Mississ+3.986
Neg logit contributions
interstitial-4.935
apult-4.690
anth-4.651
colored-4.640
-4.350
Token ()
Token ID7499
Feature activation+1.62e-01

Pos logit contributions
interstitial+0.002
apult+0.002
anth+0.002
colored+0.002
 Title+0.002
Neg logit contributions
 contrace-0.003
 dstg-0.003
 Krishna-0.003
 Mississ-0.003
 Dru-0.003
Token ->
Token ID4613
Feature activation-2.68e-02

Pos logit contributions
interstitial+0.097
apult+0.096
anth+0.093
colored+0.093
 Title+0.089
Neg logit contributions
 contrace-0.159
 dstg-0.149
 Krishna-0.141
 Mississ-0.139
 Dru-0.139
Token Atomic
Token ID28976
Feature activation+1.48e+00

Pos logit contributions
 contrace+0.027
 dstg+0.025
 Krishna+0.024
 Mississ+0.024
 Dru+0.023
Neg logit contributions
interstitial-0.016
apult-0.015
anth-0.015
colored-0.015
 Title-0.014
Token <
Token ID1279
Feature activation+1.31e+00

Pos logit contributions
interstitial+1.284
apult+1.275
colored+1.245
anth+1.239
 Title+1.216
Neg logit contributions
 contrace-1.061
 dstg-0.969
 Krishna-0.895
 Mississ-0.877
 Dru-0.873
Token Hide
Token ID10415
Feature activation+5.35e-01

Pos logit contributions
 contrace+1.361
 dstg+1.286
 Krishna+1.218
 Mississ+1.206
 Dru+1.202
Neg logit contributions
interstitial-0.942
apult-0.913
anth-0.889
colored-0.885
 Title-0.840
Token Caption
Token ID11260
Feature activation-1.68e+00

Pos logit contributions
interstitial+0.301
apult+0.293
anth+0.284
colored+0.282
 Title+0.270
Neg logit contributions
 contrace-0.547
 dstg-0.515
 Krishna-0.488
 Mississ-0.483
 Dru-0.482
Token 4
Token ID604
Feature activation+1.84e+00

Pos logit contributions
 contrace+1.593
 dstg+1.527
 Krishna+1.467
 Mississ+1.452
 Dru+1.447
Neg logit contributions
interstitial-1.048
apult-1.003
colored-0.972
anth-0.971
 Title-0.889
Token of
Token ID286
Feature activation-8.21e-01

Pos logit contributions
interstitial+1.195
apult+1.174
anth+1.153
colored+1.147
 Title+1.111
Neg logit contributions
 contrace-1.744
 dstg-1.599
 Krishna-1.503
 Mississ-1.491
 Dru-1.484
Token 15
Token ID1315
Feature activation+4.43e-01

Pos logit contributions
 contrace+0.808
 dstg+0.766
 Krishna+0.731
 Mississ+0.724
 Dru+0.721
Neg logit contributions
interstitial-0.488
apult-0.473
anth-0.459
colored-0.456
 Title-0.428
Token Photos
Token ID9434
Feature activation-6.11e+00

Pos logit contributions
interstitial+0.372
apult+0.365
anth+0.358
colored+0.356
 Title+0.345
Neg logit contributions
 contrace-0.330
 dstg-0.304
 Krishna-0.283
 Mississ-0.279
 Dru-0.277
Token:
Token ID25
Feature activation-3.01e+00

Pos logit contributions
 dstg+2.923
 contrace+2.901
 Dru+2.678
 Krishna+2.641
 Mississ+2.628
Neg logit contributions
interstitial-6.336
apult-6.125
colored-5.979
anth-5.957
-5.641
Token Carly
Token ID35982
Feature activation+5.56e-01

Pos logit contributions
 contrace+2.473
 dstg+2.327
 Krishna+2.217
 Mississ+2.208
 Dru+2.190
Neg logit contributions
interstitial-2.287
apult-2.213
anth-2.153
colored-2.151
 Title-2.020
Token Fiorina
Token ID49028
Feature activation-6.41e-01

Pos logit contributions
interstitial+0.456
apult+0.450
anth+0.441
colored+0.439
 Title+0.426
Neg logit contributions
 contrace-0.424
 dstg-0.391
 Krishna-0.361
 Mississ-0.357
 Dru-0.353
Token's
Token ID338
Feature activation-4.40e-01

Pos logit contributions
 contrace+0.501
 dstg+0.462
 Krishna+0.432
 Mississ+0.426
 Dru+0.424
Neg logit contributions
interstitial-0.514
apult-0.504
anth-0.494
colored-0.491
 Title-0.475
Token political
Token ID1964
Feature activation+3.15e-01

Pos logit contributions
 contrace+0.364
 dstg+0.338
 Krishna+0.317
 Mississ+0.313
 Dru+0.311
Neg logit contributions
interstitial-0.334
apult-0.326
anth-0.320
colored-0.318
 Title-0.307
TokenPhone
Token ID6132
Feature activation+8.38e-02

Pos logit contributions
 contrace+4.553
 dstg+4.294
 Krishna+4.054
 Mississ+4.001
 Dru+3.967
Neg logit contributions
apult-3.493
interstitial-3.485
anth-3.320
colored-3.286
 Title-3.196
TokenList
Token ID8053
Feature activation-1.72e-01

Pos logit contributions
interstitial+0.062
apult+0.061
anth+0.060
colored+0.060
 Title+0.058
Neg logit contributions
 contrace-0.070
 dstg-0.065
 Krishna-0.061
 Mississ-0.060
 Dru-0.060
TokenCtrl
Token ID40069
Feature activation-2.03e+00

Pos logit contributions
 contrace+0.152
 dstg+0.141
 Krishna+0.133
 Mississ+0.131
 Dru+0.131
Neg logit contributions
interstitial-0.122
apult-0.119
anth-0.116
colored-0.116
 Title-0.112
Token">
Token ID5320
Feature activation-1.96e+00

Pos logit contributions
 contrace+1.532
 dstg+1.415
 Krishna+1.314
 Mississ+1.298
 Dru+1.292
Neg logit contributions
interstitial-1.679
apult-1.643
anth-1.613
colored-1.604
 Title-1.548
Token <
Token ID1279
Feature activation-1.05e+00

Pos logit contributions
 contrace+1.325
 dstg+1.215
 Krishna+1.121
 Mississ+1.102
 Dru+1.098
Neg logit contributions
interstitial-1.772
apult-1.744
anth-1.707
colored-1.699
 Title-1.641
Tokenul
Token ID377
Feature activation-6.07e+00

Pos logit contributions
 contrace+0.951
 dstg+0.892
 Krishna+0.839
 Mississ+0.830
 Dru+0.827
Neg logit contributions
interstitial-0.700
apult-0.686
anth-0.666
colored-0.661
 Title-0.636
Token>
Token ID29
Feature activation-2.62e+00

Pos logit contributions
 contrace+4.942
 dstg+4.653
 Dru+4.343
 Krishna+4.326
 Mississ+4.304
Neg logit contributions
interstitial-4.554
apult-4.457
anth-4.299
colored-4.255
-3.986
Token <
Token ID1279
Feature activation-1.07e+00

Pos logit contributions
 contrace+1.681
 dstg+1.538
 Krishna+1.414
 Mississ+1.388
 Dru+1.383
Neg logit contributions
interstitial-2.442
apult-2.414
anth-2.359
colored-2.343
 Title-2.268
Tokenli
Token ID4528
Feature activation-3.86e+00

Pos logit contributions
 contrace+1.115
 dstg+1.057
 Krishna+1.001
 Mississ+0.991
 Dru+0.987
Neg logit contributions
interstitial-0.574
apult-0.562
anth-0.537
colored-0.531
 Title-0.505
Token ng
Token ID23370
Feature activation-3.32e+00

Pos logit contributions
 contrace+3.094
 dstg+2.904
 Krishna+2.695
 Dru+2.688
 Mississ+2.671
Neg logit contributions
interstitial-2.974
apult-2.900
anth-2.833
colored-2.813
 Title-2.674
Token-
Token ID12
Feature activation-1.57e+00

Pos logit contributions
 contrace+2.518
 dstg+2.338
 Krishna+2.181
 Mississ+2.158
 Dru+2.148
Neg logit contributions
interstitial-2.713
apult-2.662
anth-2.614
colored-2.588
 Title-2.492
Tokenbright
Token ID29199
Feature activation+1.99e+00

Pos logit contributions
interstitial+0.121
apult+0.118
anth+0.116
colored+0.115
 Title+0.110
Neg logit contributions
 contrace-0.184
 dstg-0.173
 Krishna-0.163
 Mississ-0.161
 Dru-0.160
Token about
Token ID546
Feature activation-5.69e-01

Pos logit contributions
interstitial+1.427
apult+1.398
anth+1.371
colored+1.368
 Title+1.332
Neg logit contributions
 contrace-1.709
 dstg-1.591
 Krishna-1.484
 Dru-1.461
 Mississ-1.460
Token the
Token ID262
Feature activation-4.20e-01

Pos logit contributions
 contrace+0.473
 dstg+0.440
 Krishna+0.411
 Mississ+0.404
 Dru+0.402
Neg logit contributions
interstitial-0.428
apult-0.418
anth-0.411
colored-0.408
 Title-0.397
Token devastating
Token ID14101
Feature activation-1.27e+00

Pos logit contributions
 contrace+0.350
 dstg+0.326
 Krishna+0.304
 Mississ+0.300
 Dru+0.298
Neg logit contributions
interstitial-0.315
apult-0.308
anth-0.303
colored-0.301
 Title-0.292
Token sanctions
Token ID9388
Feature activation-6.90e-01

Pos logit contributions
 contrace+1.048
 dstg+0.973
 Krishna+0.911
 Mississ+0.898
 Dru+0.895
Neg logit contributions
interstitial-0.970
apult-0.949
anth-0.930
colored-0.924
 Title-0.894
Token Washington
Token ID2669
Feature activation-6.02e+00

Pos logit contributions
 contrace+0.584
 dstg+0.543
 Krishna+0.509
 Mississ+0.501
 Dru+0.499
Neg logit contributions
interstitial-0.507
apult-0.497
anth-0.487
colored-0.485
 Title-0.471
Token imposed
Token ID10893
Feature activation+1.08e+00

Pos logit contributions
 contrace+4.653
 dstg+4.122
 Dru+3.962
 Mississ+3.954
 Krishna+3.953
Neg logit contributions
interstitial-4.894
apult-4.726
anth-4.622
colored-4.589
-4.323
Token on
Token ID319
Feature activation-1.26e-01

Pos logit contributions
interstitial+0.879
apult+0.864
anth+0.849
colored+0.845
 Title+0.824
Neg logit contributions
 contrace-0.829
 dstg-0.765
 Krishna-0.712
 Mississ-0.700
 Dru-0.696
Token Iraq
Token ID3908
Feature activation-7.97e-01

Pos logit contributions
 contrace+0.103
 dstg+0.095
 Krishna+0.089
 Mississ+0.088
 Dru+0.087
Neg logit contributions
interstitial-0.096
apult-0.094
anth-0.092
colored-0.092
 Title-0.089
Token after
Token ID706
Feature activation+2.87e-01

Pos logit contributions
 contrace+0.649
 dstg+0.602
 Krishna+0.564
 Mississ+0.557
 Dru+0.555
Neg logit contributions
interstitial-0.614
apult-0.600
anth-0.588
colored-0.584
 Title-0.565
Token the
Token ID262
Feature activation+2.14e-01

Pos logit contributions
interstitial+0.215
apult+0.210
anth+0.205
colored+0.204
 Title+0.197
Neg logit contributions
 contrace-0.240
 dstg-0.223
 Krishna-0.210
 Mississ-0.207
 Dru-0.206
Token Hide
Token ID10415
Feature activation+7.89e-01

Pos logit contributions
 contrace+0.020
 dstg+0.018
 Krishna+0.017
 Mississ+0.017
 Dru+0.017
Neg logit contributions
interstitial-0.018
apult-0.017
anth-0.017
colored-0.017
 Title-0.016
Token Caption
Token ID11260
Feature activation-1.76e+00

Pos logit contributions
interstitial+0.443
apult+0.431
anth+0.418
colored+0.415
 Title+0.398
Neg logit contributions
 contrace-0.810
 dstg-0.760
 Krishna-0.721
 Mississ-0.714
 Dru-0.711
Token 7
Token ID767
Feature activation+1.65e-01

Pos logit contributions
 contrace+1.371
 dstg+1.326
 Krishna+1.236
 Mississ+1.218
 Dru+1.209
Neg logit contributions
interstitial-1.393
apult-1.348
anth-1.323
colored-1.312
 Title-1.234
Token of
Token ID286
Feature activation-2.49e-01

Pos logit contributions
interstitial+0.115
apult+0.111
anth+0.108
colored+0.108
 Title+0.103
Neg logit contributions
 contrace-0.145
 dstg-0.138
 Krishna-0.130
 Mississ-0.128
 Dru-0.128
Token 15
Token ID1315
Feature activation-8.34e-01

Pos logit contributions
 contrace+0.253
 dstg+0.239
 Krishna+0.227
 Mississ+0.224
 Dru+0.223
Neg logit contributions
interstitial-0.142
apult-0.137
anth-0.134
colored-0.133
 Title-0.126
Token Photos
Token ID9434
Feature activation-5.84e+00

Pos logit contributions
 contrace+0.571
 dstg+0.543
 Krishna+0.502
 Dru+0.494
 Mississ+0.494
Neg logit contributions
interstitial-0.739
apult-0.720
anth-0.706
colored-0.702
 Title-0.674
Token:
Token ID25
Feature activation-2.04e+00

Pos logit contributions
 dstg+2.722
 Krishna+2.475
 Dru+2.466
 contrace+2.454
 Mississ+2.441
Neg logit contributions
interstitial-6.277
apult-5.999
colored-5.817
anth-5.752
ModLoader-5.477
Token Carly
Token ID35982
Feature activation+1.36e+00

Pos logit contributions
 contrace+1.570
 dstg+1.550
 Krishna+1.484
 Dru+1.471
 Mississ+1.458
Neg logit contributions
interstitial-1.634
apult-1.530
anth-1.509
colored-1.507
 Title-1.381
Token Fiorina
Token ID49028
Feature activation+4.42e-01

Pos logit contributions
interstitial+1.170
apult+1.142
anth+1.120
colored+1.117
 Title+1.080
Neg logit contributions
 contrace-0.986
 dstg-0.913
 Krishna-0.847
 Mississ-0.833
 Dru-0.832
Token's
Token ID338
Feature activation-3.21e-01

Pos logit contributions
interstitial+0.342
apult+0.336
anth+0.331
colored+0.328
 Title+0.321
Neg logit contributions
 contrace-0.361
 dstg-0.330
 Krishna-0.306
 Mississ-0.303
 Dru-0.301
Token political
Token ID1964
Feature activation+8.51e-01

Pos logit contributions
 contrace+0.268
 dstg+0.251
 Krishna+0.238
 Mississ+0.235
 Dru+0.233
Neg logit contributions
interstitial-0.238
apult-0.232
anth-0.227
colored-0.225
 Title-0.215
Token {
Token ID1391
Feature activation+1.70e-01

Pos logit contributions
 contrace+2.290
 dstg+2.140
 Krishna+2.016
 Dru+1.984
 Mississ+1.979
Neg logit contributions
interstitial-2.072
apult-2.011
anth-1.956
colored-1.939
 Title-1.859
Token const
Token ID1500
Feature activation-1.76e+00

Pos logit contributions
interstitial+0.132
apult+0.129
anth+0.126
colored+0.125
 Title+0.121
Neg logit contributions
 contrace-0.139
 dstg-0.129
 Krishna-0.120
 Mississ-0.119
 Dru-0.118
Token float
Token ID12178
Feature activation-1.47e+00

Pos logit contributions
 contrace+1.549
 dstg+1.452
 Krishna+1.366
 Dru+1.352
 Mississ+1.348
Neg logit contributions
interstitial-1.234
apult-1.197
anth-1.166
colored-1.155
 Title-1.100
Token f
Token ID277
Feature activation-2.38e+00

Pos logit contributions
 contrace+1.280
 dstg+1.200
 Krishna+1.122
 Dru+1.114
 Mississ+1.113
Neg logit contributions
interstitial-1.054
apult-1.022
anth-0.999
colored-0.986
 Title-0.948
TokenMass
Token ID20273
Feature activation-3.04e+00

Pos logit contributions
 contrace+2.075
 dstg+1.954
 Krishna+1.827
 Mississ+1.809
 Dru+1.798
Neg logit contributions
interstitial-1.673
apult-1.636
anth-1.605
colored-1.570
 Title-1.522
Token =
Token ID796
Feature activation-5.72e+00

Pos logit contributions
 contrace+2.433
 dstg+2.286
 Krishna+2.113
 Dru+2.101
 Mississ+2.089
Neg logit contributions
interstitial-2.361
apult-2.307
anth-2.242
colored-2.219
 Title-2.142
Token (
Token ID357
Feature activation-1.83e+00

Pos logit contributions
 contrace+4.992
 dstg+4.640
 Dru+4.363
 Krishna+4.330
 Mississ+4.310
Neg logit contributions
interstitial-3.997
apult-3.826
anth-3.743
colored-3.728
-3.458
Token m
Token ID285
Feature activation+3.25e-01

Pos logit contributions
 contrace+1.580
 dstg+1.472
 Krishna+1.373
 Dru+1.359
 Mississ+1.356
Neg logit contributions
interstitial-1.314
apult-1.279
anth-1.248
colored-1.238
 Title-1.188
TokenD
Token ID35
Feature activation-7.76e-02

Pos logit contributions
interstitial+0.220
apult+0.215
anth+0.210
colored+0.209
 Title+0.201
Neg logit contributions
 contrace-0.295
 dstg-0.275
 Krishna-0.259
 Mississ-0.256
 Dru-0.255
Tokenensity
Token ID6377
Feature activation-6.29e-02

Pos logit contributions
 contrace+0.075
 dstg+0.071
 Krishna+0.067
 Mississ+0.066
 Dru+0.066
Neg logit contributions
interstitial-0.048
apult-0.046
anth-0.045
colored-0.045
 Title-0.043
Token +
Token ID1343
Feature activation-1.27e+00

Pos logit contributions
 contrace+0.054
 dstg+0.050
 Krishna+0.047
 Mississ+0.046
 Dru+0.046
Neg logit contributions
interstitial-0.046
apult-0.045
anth-0.044
colored-0.044
 Title-0.042
Token Hide
Token ID10415
Feature activation+4.47e-01

Pos logit contributions
interstitial+0.650
apult+0.636
anth+0.622
colored+0.618
 Title+0.599
Neg logit contributions
 contrace-0.765
 dstg-0.711
 Krishna-0.666
 Mississ-0.657
 Dru-0.654
Token Caption
Token ID11260
Feature activation-1.29e+00

Pos logit contributions
interstitial+0.254
apult+0.246
anth+0.240
colored+0.238
 Title+0.227
Neg logit contributions
 contrace-0.455
 dstg-0.428
 Krishna-0.407
 Mississ-0.402
 Dru-0.401
Token 5
Token ID642
Feature activation+1.30e+00

Pos logit contributions
 contrace+1.177
 dstg+1.151
 Krishna+1.088
 Dru+1.073
 Mississ+1.069
Neg logit contributions
interstitial-0.842
apult-0.818
colored-0.788
anth-0.782
 Title-0.719
Token of
Token ID286
Feature activation-1.41e-01

Pos logit contributions
interstitial+0.851
apult+0.834
anth+0.818
colored+0.813
 Title+0.787
Neg logit contributions
 contrace-1.209
 dstg-1.115
 Krishna-1.052
 Mississ-1.040
 Dru-1.034
Token 15
Token ID1315
Feature activation+9.13e-02

Pos logit contributions
 contrace+0.145
 dstg+0.136
 Krishna+0.129
 Mississ+0.128
 Dru+0.127
Neg logit contributions
interstitial-0.079
apult-0.077
anth-0.075
colored-0.074
 Title-0.071
Token Photos
Token ID9434
Feature activation-5.71e+00

Pos logit contributions
interstitial+0.078
apult+0.076
anth+0.075
colored+0.075
 Title+0.072
Neg logit contributions
 contrace-0.067
 dstg-0.061
 Krishna-0.057
 Mississ-0.056
 Dru-0.056
Token:
Token ID25
Feature activation-2.43e+00

Pos logit contributions
 dstg+2.657
 Krishna+2.413
 Dru+2.406
 Mississ+2.381
 contrace+2.373
Neg logit contributions
interstitial-6.114
apult-5.855
colored-5.677
anth-5.629
ModLoader-5.333
Token Carly
Token ID35982
Feature activation+7.78e-01

Pos logit contributions
 contrace+1.900
 dstg+1.849
 Krishna+1.778
 Dru+1.762
 Mississ+1.757
Neg logit contributions
interstitial-1.913
apult-1.805
colored-1.780
anth-1.779
 Title-1.627
Token Fiorina
Token ID49028
Feature activation+1.66e-01

Pos logit contributions
interstitial+0.668
apult+0.652
anth+0.640
colored+0.638
 Title+0.617
Neg logit contributions
 contrace-0.565
 dstg-0.521
 Krishna-0.484
 Mississ-0.476
 Dru-0.475
Token's
Token ID338
Feature activation-7.04e-01

Pos logit contributions
interstitial+0.129
apult+0.127
anth+0.124
colored+0.124
 Title+0.121
Neg logit contributions
 contrace-0.134
 dstg-0.123
 Krishna-0.114
 Mississ-0.113
 Dru-0.112
Token political
Token ID1964
Feature activation+2.85e-01

Pos logit contributions
 contrace+0.586
 dstg+0.547
 Krishna+0.520
 Mississ+0.513
 Dru+0.508
Neg logit contributions
interstitial-0.523
apult-0.511
anth-0.500
colored-0.496
 Title-0.473
Token
Token ID198
Feature activation+1.40e+00

Pos logit contributions
interstitial+0.980
apult+0.958
anth+0.938
colored+0.930
 Title+0.892
Neg logit contributions
 contrace-2.058
 dstg-1.912
 Krishna-1.818
 Mississ-1.801
 Dru-1.791
Tokenimpl
Token ID23928
Feature activation-1.87e+00

Pos logit contributions
interstitial+1.033
apult+1.006
anth+0.996
colored+0.989
 Title+0.942
Neg logit contributions
 contrace-1.196
 dstg-1.108
 Krishna-1.050
 Mississ-1.039
 Dru-1.027
Token Board
Token ID5926
Feature activation+5.87e-01

Pos logit contributions
 contrace+1.467
 dstg+1.358
 Krishna+1.270
 Mississ+1.254
 Dru+1.251
Neg logit contributions
interstitial-1.486
apult-1.453
anth-1.430
colored-1.418
 Title-1.367
Token {
Token ID1391
Feature activation+1.11e+00

Pos logit contributions
interstitial+0.434
apult+0.424
colored+0.412
anth+0.412
 Title+0.400
Neg logit contributions
 contrace-0.499
 dstg-0.463
 Krishna-0.432
 Mississ-0.427
 Dru-0.426
Token pub
Token ID2240
Feature activation+1.58e-01

Pos logit contributions
interstitial+0.802
apult+0.783
colored+0.766
anth+0.762
 Title+0.746
Neg logit contributions
 contrace-0.961
 dstg-0.894
 Krishna-0.838
 Mississ-0.829
 Dru-0.821
Token fn
Token ID24714
Feature activation-5.67e+00

Pos logit contributions
interstitial+0.098
apult+0.096
anth+0.093
colored+0.093
 Title+0.088
Neg logit contributions
 contrace-0.152
 dstg-0.143
 Krishna-0.135
 Mississ-0.134
 Dru-0.133
Token copy
Token ID4866
Feature activation-1.51e+00

Pos logit contributions
 contrace+4.902
 dstg+4.417
 Krishna+4.266
 Mississ+4.231
 Dru+4.214
Neg logit contributions
interstitial-3.980
apult-3.858
anth-3.858
colored-3.761
-3.548
Token_
Token ID62
Feature activation-2.15e+00

Pos logit contributions
 contrace+1.192
 dstg+1.102
 Krishna+1.029
 Mississ+1.015
 Dru+1.010
Neg logit contributions
interstitial-1.203
apult-1.178
anth-1.155
colored-1.148
 Title-1.112
Tokenboard
Token ID3526
Feature activation-2.26e+00

Pos logit contributions
 contrace+1.926
 dstg+1.800
 Krishna+1.696
 Mississ+1.679
 Dru+1.669
Neg logit contributions
interstitial-1.456
apult-1.427
anth-1.392
colored-1.379
 Title-1.342
Token (
Token ID357
Feature activation-1.65e-02

Pos logit contributions
 contrace+1.756
 dstg+1.622
 Krishna+1.514
 Mississ+1.495
 Dru+1.486
Neg logit contributions
interstitial-1.823
apult-1.786
anth-1.752
colored-1.741
 Title-1.687
Token &
Token ID1222
Feature activation-1.75e+00

Pos logit contributions
 contrace+0.014
 dstg+0.013
 Krishna+0.012
 Mississ+0.012
 Dru+0.012
Neg logit contributions
interstitial-0.012
apult-0.012
anth-0.012
colored-0.012
 Title-0.011
Token Hide
Token ID10415
Feature activation-7.18e-01

Pos logit contributions
 contrace+0.267
 dstg+0.249
 Krishna+0.234
 Mississ+0.232
 Dru+0.231
Neg logit contributions
interstitial-0.243
apult-0.236
anth-0.232
colored-0.231
 Title-0.220
Token Caption
Token ID11260
Feature activation-1.44e+00

Pos logit contributions
 contrace+0.694
 dstg+0.667
 Krishna+0.635
 Mississ+0.629
 Dru+0.627
Neg logit contributions
interstitial-0.432
apult-0.415
anth-0.405
colored-0.403
 Title-0.375
Token 12
Token ID1105
Feature activation-3.57e-01

Pos logit contributions
 contrace+1.273
 dstg+1.212
 Krishna+1.155
 Mississ+1.140
 Dru+1.139
Neg logit contributions
interstitial-0.994
apult-0.963
anth-0.932
colored-0.928
 Title-0.877
Token of
Token ID286
Feature activation-3.08e-01

Pos logit contributions
 contrace+0.305
 dstg+0.292
 Krishna+0.275
 Mississ+0.272
 Dru+0.271
Neg logit contributions
interstitial-0.256
apult-0.247
anth-0.240
colored-0.239
 Title-0.228
Token 15
Token ID1315
Feature activation-1.29e+00

Pos logit contributions
 contrace+0.311
 dstg+0.294
 Krishna+0.279
 Mississ+0.276
 Dru+0.275
Neg logit contributions
interstitial-0.177
apult-0.171
anth-0.166
colored-0.165
 Title-0.157
Token Photos
Token ID9434
Feature activation-5.67e+00

Pos logit contributions
 contrace+0.859
 dstg+0.828
 Krishna+0.766
 Dru+0.755
 Mississ+0.753
Neg logit contributions
interstitial-1.161
apult-1.128
anth-1.103
colored-1.100
 Title-1.050
Token:
Token ID25
Feature activation-2.06e+00

Pos logit contributions
 dstg+2.688
 Krishna+2.443
 contrace+2.434
 Dru+2.433
 Mississ+2.407
Neg logit contributions
interstitial-6.064
apult-5.799
colored-5.630
anth-5.560
-5.287
Token Carly
Token ID35982
Feature activation+7.45e-01

Pos logit contributions
 contrace+1.579
 dstg+1.567
 Krishna+1.496
 Dru+1.482
 Mississ+1.469
Neg logit contributions
interstitial-1.642
apult-1.537
anth-1.515
colored-1.513
 Title-1.388
Token Fiorina
Token ID49028
Feature activation+4.75e-01

Pos logit contributions
interstitial+0.653
apult+0.634
anth+0.621
colored+0.621
 Title+0.598
Neg logit contributions
 contrace-0.526
 dstg-0.492
 Krishna-0.457
 Dru-0.449
 Mississ-0.448
Token's
Token ID338
Feature activation-1.84e-01

Pos logit contributions
interstitial+0.373
apult+0.367
anth+0.360
colored+0.358
 Title+0.349
Neg logit contributions
 contrace-0.381
 dstg-0.350
 Krishna-0.325
 Mississ-0.322
 Dru-0.320
Token political
Token ID1964
Feature activation+2.81e-01

Pos logit contributions
 contrace+0.155
 dstg+0.145
 Krishna+0.138
 Mississ+0.136
 Dru+0.135
Neg logit contributions
interstitial-0.135
apult-0.132
anth-0.129
colored-0.128
 Title-0.122
Token the
Token ID262
Feature activation+1.82e-02

Pos logit contributions
 contrace+0.319
 dstg+0.296
 Krishna+0.276
 Mississ+0.273
 Dru+0.271
Neg logit contributions
interstitial-0.291
apult-0.285
anth-0.279
colored-0.277
 Title-0.270
Token must
Token ID1276
Feature activation-8.23e-01

Pos logit contributions
interstitial+0.014
apult+0.014
anth+0.013
colored+0.013
 Title+0.013
Neg logit contributions
 contrace-0.015
 dstg-0.014
 Krishna-0.013
 Mississ-0.013
 Dru-0.013
Token-
Token ID12
Feature activation-1.76e-01

Pos logit contributions
 contrace+0.641
 dstg+0.592
 Krishna+0.552
 Mississ+0.544
 Dru+0.542
Neg logit contributions
interstitial-0.664
apult-0.650
anth-0.638
colored-0.634
 Title-0.614
Tokenpass
Token ID6603
Feature activation+2.08e+00

Pos logit contributions
 contrace+0.133
 dstg+0.122
 Krishna+0.114
 Mississ+0.112
 Dru+0.111
Neg logit contributions
interstitial-0.146
apult-0.143
anth-0.140
colored-0.140
 Title-0.135
Token measures
Token ID5260
Feature activation-1.30e+00

Pos logit contributions
interstitial+1.559
apult+1.535
anth+1.500
colored+1.490
 Title+1.466
Neg logit contributions
 contrace-1.725
 dstg-1.592
 Krishna-1.495
 Mississ-1.468
 Dru-1.466
Token Congress
Token ID3162
Feature activation-5.66e+00

Pos logit contributions
 contrace+1.048
 dstg+0.976
 Krishna+0.916
 Mississ+0.905
 Dru+0.901
Neg logit contributions
interstitial-1.009
apult-0.981
anth-0.964
colored-0.958
 Title-0.919
Token will
Token ID481
Feature activation-3.44e-01

Pos logit contributions
 contrace+3.753
 dstg+3.345
 Mississ+3.210
 Krishna+3.197
 Dru+3.153
Neg logit contributions
interstitial-5.221
apult-4.960
colored-4.883
anth-4.875
 Title-4.644
Token take
Token ID1011
Feature activation-5.83e-01

Pos logit contributions
 contrace+0.280
 dstg+0.260
 Krishna+0.243
 Mississ+0.240
 Dru+0.239
Neg logit contributions
interstitial-0.265
apult-0.259
anth-0.254
colored-0.252
 Title-0.244
Token up
Token ID510
Feature activation+6.51e-01

Pos logit contributions
 contrace+0.490
 dstg+0.456
 Krishna+0.429
 Mississ+0.425
 Dru+0.422
Neg logit contributions
interstitial-0.435
apult-0.422
anth-0.413
colored-0.411
 Title-0.394
Token when
Token ID618
Feature activation+1.21e+00

Pos logit contributions
interstitial+0.480
apult+0.470
anth+0.460
colored+0.458
 Title+0.443
Neg logit contributions
 contrace-0.551
 dstg-0.512
 Krishna-0.480
 Mississ-0.473
 Dru-0.472
Token it
Token ID340
Feature activation+9.25e-01

Pos logit contributions
interstitial+0.831
apult+0.813
anth+0.796
colored+0.790
 Title+0.774
Neg logit contributions
 contrace-1.084
 dstg-1.013
 Krishna-0.947
 Dru-0.932
 Mississ-0.932
Token The
Token ID383
Feature activation+1.35e-02

Pos logit contributions
 contrace+0.367
 dstg+0.348
 Krishna+0.331
 Mississ+0.327
 Dru+0.326
Neg logit contributions
interstitial-0.258
apult-0.249
anth-0.242
colored-0.241
 Title-0.228
Token Chronicle
Token ID14160
Feature activation+3.76e+00

Pos logit contributions
interstitial+0.010
apult+0.010
anth+0.010
colored+0.010
 Title+0.009
Neg logit contributions
 contrace-0.011
 dstg-0.011
 Krishna-0.010
 Mississ-0.010
 Dru-0.010
Token 3
Token ID513
Feature activation-2.62e+00

Pos logit contributions
interstitial+2.306
apult+2.262
anth+2.208
colored+2.190
 Title+2.132
Neg logit contributions
 contrace-3.648
 dstg-3.356
 Krishna-3.215
 Mississ-3.165
 Dru-3.154
Token of
Token ID286
Feature activation-1.29e+00

Pos logit contributions
 dstg+2.031
 contrace+2.008
 Krishna+1.905
 Dru+1.881
 Mississ+1.857
Neg logit contributions
interstitial-2.002
apult-1.928
anth-1.868
colored-1.847
 Title-1.738
Token 15
Token ID1315
Feature activation-2.62e-01

Pos logit contributions
 contrace+1.278
 dstg+1.214
 Krishna+1.156
 Mississ+1.142
 Dru+1.137
Neg logit contributions
interstitial-0.751
apult-0.729
anth-0.706
colored-0.703
 Title-0.664
Token Photo
Token ID5555
Feature activation-5.66e+00

Pos logit contributions
 contrace+0.217
 dstg+0.205
 Krishna+0.192
 Dru+0.189
 Mississ+0.189
Neg logit contributions
interstitial-0.196
apult-0.191
anth-0.186
colored-0.185
 Title-0.177
Token:
Token ID25
Feature activation-1.83e+00

Pos logit contributions
 dstg+2.762
 contrace+2.614
 Krishna+2.515
 Dru+2.474
 Mississ+2.437
Neg logit contributions
interstitial-5.891
apult-5.690
anth-5.515
colored-5.494
 Title-5.197
Token Le
Token ID1004
Feature activation+1.21e+00

Pos logit contributions
 contrace+1.520
 dstg+1.425
 Krishna+1.362
 Dru+1.339
 Mississ+1.331
Neg logit contributions
interstitial-1.367
apult-1.333
colored-1.295
anth-1.293
 Title-1.220
Tokena
Token ID64
Feature activation+9.17e-01

Pos logit contributions
interstitial+0.773
apult+0.757
anth+0.744
colored+0.733
 Title+0.708
Neg logit contributions
 contrace-1.157
 dstg-1.071
 Krishna-1.010
 Mississ-1.000
 Dru-0.993
Token Suzuki
Token ID35807
Feature activation+1.44e-01

Pos logit contributions
interstitial+0.492
apult+0.479
anth+0.465
colored+0.461
 Title+0.443
Neg logit contributions
 contrace-0.961
 dstg-0.903
 Krishna-0.856
 Mississ-0.849
 Dru-0.844
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
interstitial+0.109
apult+0.105
anth+0.103
colored+0.102
 Title+0.098
Neg logit contributions
 contrace-0.119
 dstg-0.113
 Krishna-0.106
 Mississ-0.105
 Dru-0.104
Token <
Token ID1279
Feature activation+8.57e-01

Pos logit contributions
interstitial+0.773
apult+0.760
colored+0.743
anth+0.743
 Title+0.722
Neg logit contributions
 contrace-0.620
 dstg-0.562
 Krishna-0.524
 Dru-0.511
 Mississ-0.510
Token T
Token ID309
Feature activation+1.20e+00

Pos logit contributions
interstitial+0.473
apult+0.461
anth+0.447
colored+0.444
 Title+0.428
Neg logit contributions
 contrace-0.882
 dstg-0.831
 Krishna-0.789
 Mississ-0.781
 Dru-0.777
Token >
Token ID1875
Feature activation+4.91e-01

Pos logit contributions
interstitial+1.027
apult+1.010
anth+0.991
colored+0.988
 Title+0.964
Neg logit contributions
 contrace-0.867
 dstg-0.794
 Krishna-0.735
 Mississ-0.725
 Dru-0.720
Token {
Token ID1391
Feature activation+2.38e+00

Pos logit contributions
interstitial+0.352
apult+0.344
anth+0.335
colored+0.334
 Title+0.326
Neg logit contributions
 contrace-0.428
 dstg-0.394
 Krishna-0.371
 Mississ-0.365
 Dru-0.364
Token pub
Token ID2240
Feature activation+1.36e+00

Pos logit contributions
interstitial+1.676
apult+1.648
colored+1.615
anth+1.600
 Title+1.585
Neg logit contributions
 contrace-2.048
 dstg-1.904
 Krishna-1.795
 Mississ-1.772
 Dru-1.755
Token fn
Token ID24714
Feature activation-5.65e+00

Pos logit contributions
interstitial+0.781
apult+0.763
anth+0.740
colored+0.738
 Title+0.711
Neg logit contributions
 contrace-1.365
 dstg-1.283
 Krishna-1.219
 Mississ-1.204
 Dru-1.198
Token load
Token ID3440
Feature activation+4.01e-01

Pos logit contributions
 contrace+4.475
 dstg+4.115
 Krishna+3.879
 Mississ+3.855
 Dru+3.828
Neg logit contributions
interstitial-4.353
apult-4.201
anth-4.198
colored-4.125
-3.900
Token <
Token ID1279
Feature activation-1.76e-01

Pos logit contributions
interstitial+0.299
apult+0.292
anth+0.285
colored+0.285
 Title+0.275
Neg logit contributions
 contrace-0.338
 dstg-0.314
 Krishna-0.294
 Mississ-0.290
 Dru-0.289
Token '
Token ID705
Feature activation-6.21e-01

Pos logit contributions
 contrace+0.160
 dstg+0.149
 Krishna+0.141
 Mississ+0.139
 Dru+0.138
Neg logit contributions
interstitial-0.119
apult-0.116
anth-0.114
colored-0.113
 Title-0.109
Tokena
Token ID64
Feature activation+1.55e+00

Pos logit contributions
 contrace+0.566
 dstg+0.531
 Krishna+0.501
 Mississ+0.494
 Dru+0.493
Neg logit contributions
interstitial-0.416
apult-0.405
anth-0.396
colored-0.393
 Title-0.378
Token >
Token ID1875
Feature activation+1.71e-01

Pos logit contributions
interstitial+0.865
apult+0.842
anth+0.817
colored+0.812
 Title+0.781
Neg logit contributions
 contrace-1.596
 dstg-1.502
 Krishna-1.427
 Mississ-1.412
 Dru-1.403
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
interstitial+0.082
apult+0.081
anth+0.079
colored+0.079
 Title+0.076
Neg logit contributions
 contrace-0.092
 dstg-0.085
 Krishna-0.080
 Mississ-0.079
 Dru-0.078
Token
Token ID198
Feature activation+5.60e-01

Pos logit contributions
 contrace+0.340
 dstg+0.319
 Krishna+0.302
 Mississ+0.298
 Dru+0.297
Neg logit contributions
interstitial-0.237
apult-0.231
anth-0.225
colored-0.224
 Title-0.214
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
interstitial+0.309
apult+0.299
anth+0.290
colored+0.287
 Title+0.273
Neg logit contributions
 contrace-0.578
 dstg-0.547
 Krishna-0.520
 Mississ-0.515
 Dru-0.514
TokenDisclaimer
Token ID19618
Feature activation-2.91e+00

Pos logit contributions
interstitial+0.151
apult+0.147
anth+0.144
colored+0.143
 Title+0.138
Neg logit contributions
 contrace-0.185
 dstg-0.172
 Krishna-0.162
 Mississ-0.160
 Dru-0.159
Token:
Token ID25
Feature activation-1.47e+00

Pos logit contributions
 contrace+1.899
 dstg+1.743
 Krishna+1.613
 Dru+1.581
 Mississ+1.577
Neg logit contributions
interstitial-2.710
apult-2.637
anth-2.583
colored-2.577
 Title-2.472
Token ©
Token ID10673
Feature activation-5.63e+00

Pos logit contributions
 contrace+1.319
 dstg+1.230
 Krishna+1.171
 Dru+1.156
 Mississ+1.152
Neg logit contributions
interstitial-1.006
apult-0.979
anth-0.955
colored-0.948
 Title-0.897
Token 2015
Token ID1853
Feature activation-4.70e-01

Pos logit contributions
 contrace+4.663
 dstg+4.379
 Krishna+4.192
 Dru+4.175
 Mississ+4.102
Neg logit contributions
interstitial-4.101
apult-3.917
anth-3.825
colored-3.766
 Title-3.551
Token Money
Token ID12911
Feature activation-4.11e+00

Pos logit contributions
 contrace+0.408
 dstg+0.380
 Krishna+0.359
 Mississ+0.354
 Dru+0.354
Neg logit contributions
interstitial-0.338
apult-0.328
anth-0.322
colored-0.319
 Title-0.306
Token Morning
Token ID14410
Feature activation-2.65e+00

Pos logit contributions
 contrace+3.037
 dstg+2.806
 Mississ+2.704
 Krishna+2.669
 Dru+2.663
Neg logit contributions
interstitial-3.372
anth-3.213
apult-3.189
colored-3.152
 Title-3.010
Token and
Token ID290
Feature activation-2.46e+00

Pos logit contributions
 contrace+2.257
 dstg+2.082
 Krishna+1.981
 Dru+1.961
 Mississ+1.961
Neg logit contributions
interstitial-1.963
apult-1.872
anth-1.843
colored-1.826
 Title-1.732
Token Money
Token ID12911
Feature activation-2.73e+00

Pos logit contributions
 contrace+2.031
 dstg+1.873
 Krishna+1.784
 Dru+1.756
 Mississ+1.747
Neg logit contributions
interstitial-1.863
apult-1.816
anth-1.784
colored-1.763
 Title-1.678
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
 contrace+0.186
 dstg+0.173
 Krishna+0.162
 Mississ+0.160
 Dru+0.160
Neg logit contributions
interstitial-0.177
apult-0.173
anth-0.169
colored-0.168
 Title-0.162
Token video
Token ID2008
Feature activation-1.44e+00

Pos logit contributions
 contrace+1.025
 dstg+0.952
 Krishna+0.901
 Mississ+0.895
 Dru+0.890
Neg logit contributions
interstitial-0.896
apult-0.876
anth-0.852
colored-0.847
 Title-0.808
Token with
Token ID351
Feature activation+1.05e-01

Pos logit contributions
 contrace+1.195
 dstg+1.109
 Krishna+1.045
 Mississ+1.033
 Dru+1.030
Neg logit contributions
interstitial-1.088
apult-1.054
colored-1.030
anth-1.028
 Title-0.985
Token #
Token ID1303
Feature activation-2.07e+00

Pos logit contributions
interstitial+0.088
apult+0.087
anth+0.085
colored+0.085
 Title+0.082
Neg logit contributions
 contrace-0.078
 dstg-0.072
 Krishna-0.067
 Mississ-0.066
 Dru-0.066
TokenAsk
Token ID25214
Feature activation-3.85e+00

Pos logit contributions
 contrace+1.439
 dstg+1.319
 Krishna+1.220
 Mississ+1.204
 Dru+1.201
Neg logit contributions
interstitial-1.811
apult-1.784
anth-1.742
colored-1.735
 Title-1.692
TokenThe
Token ID464
Feature activation-5.61e+00

Pos logit contributions
 contrace+3.285
 dstg+3.052
 Krishna+2.895
 Dru+2.872
 Mississ+2.850
Neg logit contributions
interstitial-2.718
apult-2.649
colored-2.570
anth-2.556
 Title-2.499
TokenD
Token ID35
Feature activation-4.32e+00

Pos logit contributions
 contrace+4.336
 dstg+4.061
 Dru+3.824
 Krishna+3.781
rists+3.724
Neg logit contributions
interstitial-4.331
apult-4.248
anth-4.155
colored-4.069
 Title-4.000
Tokenubs
Token ID23161
Feature activation-1.35e+00

Pos logit contributions
 contrace+2.844
 dstg+2.743
rists+2.514
 Dru+2.498
 Krishna+2.495
Neg logit contributions
interstitial-3.807
apult-3.666
anth-3.570
colored-3.546
 Title-3.520
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
 contrace+1.051
 dstg+0.979
 Krishna+0.914
 Mississ+0.904
 Dru+0.900
Neg logit contributions
interstitial-1.066
apult-1.041
anth-1.018
colored-1.013
 Title-0.978
Token then
Token ID788
Feature activation+9.43e-01

Pos logit contributions
 contrace+0.858
 dstg+0.798
 Krishna+0.754
 Mississ+0.745
 Dru+0.743
Neg logit contributions
interstitial-0.748
apult-0.731
anth-0.712
colored-0.711
 Title-0.681
Token tune
Token ID14009
Feature activation-1.35e+00

Pos logit contributions
interstitial+0.733
apult+0.716
anth+0.704
colored+0.699
 Title+0.684
Neg logit contributions
 contrace-0.763
 dstg-0.708
 Krishna-0.655
 Mississ-0.646
 Dru-0.642
Token<
Token ID27
Feature activation-8.03e-01

Pos logit contributions
interstitial+0.647
apult+0.628
anth+0.621
colored+0.619
 Title+0.593
Neg logit contributions
 contrace-0.731
 dstg-0.677
 Krishna-0.639
 Mississ-0.629
 Dru-0.626
Tokenbody
Token ID2618
Feature activation-2.67e+00

Pos logit contributions
 contrace+0.720
 dstg+0.672
 Krishna+0.633
 Mississ+0.626
 Dru+0.624
Neg logit contributions
interstitial-0.551
apult-0.540
anth-0.526
colored-0.522
 Title-0.503
Token ng
Token ID23370
Feature activation-4.45e+00

Pos logit contributions
 contrace+2.264
 dstg+2.116
 Krishna+1.977
 Mississ+1.967
 Dru+1.963
Neg logit contributions
interstitial-1.954
apult-1.899
anth-1.862
colored-1.831
 Title-1.746
Token-
Token ID12
Feature activation-2.05e+00

Pos logit contributions
 contrace+3.134
 dstg+2.969
 Krishna+2.763
 Mississ+2.735
 Dru+2.728
Neg logit contributions
interstitial-3.749
apult-3.679
anth-3.601
colored-3.564
 Title-3.433
Tokencontroller
Token ID36500
Feature activation-2.83e+00

Pos logit contributions
 contrace+1.726
 dstg+1.609
 Krishna+1.508
 Mississ+1.488
 Dru+1.481
Neg logit contributions
interstitial-1.505
apult-1.485
anth-1.447
colored-1.431
 Title-1.393
Token="
Token ID2625
Feature activation-5.60e+00

Pos logit contributions
 contrace+2.076
 dstg+1.918
 Krishna+1.764
 Mississ+1.750
 Dru+1.741
Neg logit contributions
interstitial-2.405
apult-2.348
anth-2.305
colored-2.283
 Title-2.196
TokenPhone
Token ID6132
Feature activation-6.29e-02

Pos logit contributions
 contrace+3.886
 dstg+3.618
 Dru+3.315
 Mississ+3.315
 Krishna+3.306
Neg logit contributions
interstitial-4.755
apult-4.712
anth-4.576
colored-4.547
 Title-4.417
TokenList
Token ID8053
Feature activation-1.07e+00

Pos logit contributions
 contrace+0.050
 dstg+0.047
 Krishna+0.044
 Mississ+0.043
 Dru+0.043
Neg logit contributions
interstitial-0.049
apult-0.048
anth-0.047
colored-0.047
 Title-0.046
TokenCtrl
Token ID40069
Feature activation-9.96e-01

Pos logit contributions
 contrace+1.001
 dstg+0.939
 Krishna+0.886
 Mississ+0.876
 Dru+0.873
Neg logit contributions
interstitial-0.699
apult-0.681
anth-0.664
colored-0.660
 Title-0.633
Token">
Token ID5320
Feature activation-1.85e+00

Pos logit contributions
 contrace+0.783
 dstg+0.722
 Krishna+0.675
 Mississ+0.665
 Dru+0.662
Neg logit contributions
interstitial-0.796
apult-0.780
anth-0.765
colored-0.761
 Title-0.738
Token <
Token ID1279
Feature activation-8.97e-01

Pos logit contributions
 contrace+1.189
 dstg+1.085
 Krishna+0.992
 Mississ+0.975
 Dru+0.972
Neg logit contributions
interstitial-1.733
apult-1.707
anth-1.674
colored-1.665
 Title-1.612
Token Hide
Token ID10415
Feature activation+5.00e-01

Pos logit contributions
interstitial+0.571
apult+0.559
anth+0.547
colored+0.544
 Title+0.527
Neg logit contributions
 contrace-0.667
 dstg-0.619
 Krishna-0.581
 Mississ-0.573
 Dru-0.570
Token Caption
Token ID11260
Feature activation-1.46e+00

Pos logit contributions
interstitial+0.285
apult+0.276
anth+0.269
colored+0.267
 Title+0.254
Neg logit contributions
 contrace-0.508
 dstg-0.479
 Krishna-0.454
 Mississ-0.450
 Dru-0.448
Token 6
Token ID718
Feature activation+5.11e-01

Pos logit contributions
 contrace+1.244
 dstg+1.180
 Krishna+1.115
 Mississ+1.101
 Dru+1.098
Neg logit contributions
interstitial-1.049
apult-1.023
anth-0.998
colored-0.989
 Title-0.942
Token of
Token ID286
Feature activation-1.09e-01

Pos logit contributions
interstitial+0.353
apult+0.343
anth+0.334
colored+0.332
 Title+0.319
Neg logit contributions
 contrace-0.456
 dstg-0.429
 Krishna-0.405
 Mississ-0.400
 Dru-0.399
Token 15
Token ID1315
Feature activation-4.13e-01

Pos logit contributions
 contrace+0.112
 dstg+0.105
 Krishna+0.100
 Mississ+0.099
 Dru+0.099
Neg logit contributions
interstitial-0.062
apult-0.060
anth-0.058
colored-0.058
 Title-0.055
Token Photos
Token ID9434
Feature activation-5.54e+00

Pos logit contributions
 contrace+0.292
 dstg+0.273
 Krishna+0.253
 Mississ+0.249
 Dru+0.248
Neg logit contributions
interstitial-0.360
apult-0.352
anth-0.346
colored-0.344
 Title-0.332
Token:
Token ID25
Feature activation-1.90e+00

Pos logit contributions
 dstg+2.609
 Krishna+2.375
 contrace+2.373
 Dru+2.362
 Mississ+2.347
Neg logit contributions
interstitial-5.930
apult-5.669
colored-5.506
anth-5.447
 Title-5.171
Token Carly
Token ID35982
Feature activation+1.33e+00

Pos logit contributions
 contrace+1.469
 dstg+1.444
 Krishna+1.384
 Dru+1.371
 Mississ+1.361
Neg logit contributions
interstitial-1.508
apult-1.413
anth-1.395
colored-1.392
 Title-1.278
Token Fiorina
Token ID49028
Feature activation+5.66e-01

Pos logit contributions
interstitial+1.145
apult+1.117
anth+1.097
colored+1.093
 Title+1.058
Neg logit contributions
 contrace-0.967
 dstg-0.895
 Krishna-0.831
 Mississ-0.817
 Dru-0.816
Token's
Token ID338
Feature activation-2.61e-01

Pos logit contributions
interstitial+0.433
apult+0.427
anth+0.420
colored+0.417
 Title+0.409
Neg logit contributions
 contrace-0.467
 dstg-0.426
 Krishna-0.394
 Mississ-0.391
 Dru-0.389
Token political
Token ID1964
Feature activation+7.73e-01

Pos logit contributions
 contrace+0.219
 dstg+0.205
 Krishna+0.194
 Mississ+0.191
 Dru+0.190
Neg logit contributions
interstitial-0.194
apult-0.189
anth-0.185
colored-0.184
 Title-0.175
Token The
Token ID383
Feature activation+3.78e-01

Pos logit contributions
 contrace+0.532
 dstg+0.506
 Krishna+0.481
 Mississ+0.475
 Dru+0.474
Neg logit contributions
interstitial-0.380
apult-0.365
anth-0.355
colored-0.354
 Title-0.333
Token Chronicle
Token ID14160
Feature activation+4.40e+00

Pos logit contributions
interstitial+0.274
apult+0.270
anth+0.264
colored+0.262
 Title+0.256
Neg logit contributions
 contrace-0.326
 dstg-0.300
 Krishna-0.281
 Mississ-0.277
 Dru-0.276
Token 4
Token ID604
Feature activation-2.91e+00

Pos logit contributions
interstitial+2.474
apult+2.414
anth+2.393
colored+2.358
 Title+2.338
Neg logit contributions
 contrace-4.539
 dstg-4.137
 Krishna-3.915
rists-3.904
 Mississ-3.868
Token of
Token ID286
Feature activation-9.18e-01

Pos logit contributions
 dstg+2.206
 contrace+2.155
 Krishna+2.072
 Dru+2.043
 Mississ+2.023
Neg logit contributions
interstitial-2.308
apult-2.192
anth-2.112
colored-2.101
 Title-1.960
Token 15
Token ID1315
Feature activation-4.83e-01

Pos logit contributions
 contrace+0.919
 dstg+0.871
 Krishna+0.828
 Mississ+0.819
 Dru+0.816
Neg logit contributions
interstitial-0.532
apult-0.515
anth-0.499
colored-0.497
 Title-0.471
Token Photo
Token ID5555
Feature activation-5.53e+00

Pos logit contributions
 contrace+0.398
 dstg+0.377
 Krishna+0.355
 Mississ+0.350
 Dru+0.350
Neg logit contributions
interstitial-0.363
apult-0.355
anth-0.345
colored-0.344
 Title-0.327
Token:
Token ID25
Feature activation-1.91e+00

Pos logit contributions
 dstg+2.704
 contrace+2.560
 Krishna+2.462
 Dru+2.431
 Mississ+2.399
Neg logit contributions
interstitial-5.776
apult-5.584
anth-5.403
colored-5.386
 Title-5.088
Token Le
Token ID1004
Feature activation+1.21e+00

Pos logit contributions
 contrace+1.592
 dstg+1.493
 Krishna+1.426
 Dru+1.403
 Mississ+1.393
Neg logit contributions
interstitial-1.423
apult-1.388
colored-1.349
anth-1.346
 Title-1.270
Tokena
Token ID64
Feature activation+1.11e+00

Pos logit contributions
interstitial+0.772
apult+0.756
anth+0.742
colored+0.732
 Title+0.706
Neg logit contributions
 contrace-1.146
 dstg-1.062
 Krishna-1.002
 Mississ-0.992
 Dru-0.986
Token Suzuki
Token ID35807
Feature activation+1.43e-01

Pos logit contributions
interstitial+0.595
apult+0.580
anth+0.564
colored+0.558
 Title+0.537
Neg logit contributions
 contrace-1.164
 dstg-1.093
 Krishna-1.036
 Mississ-1.027
 Dru-1.022
Token,
Token ID11
Feature activation-6.68e-01

Pos logit contributions
interstitial+0.107
apult+0.104
anth+0.101
colored+0.101
 Title+0.097
Neg logit contributions
 contrace-0.118
 dstg-0.112
 Krishna-0.105
 Mississ-0.104
 Dru-0.104
Token:
Token ID25
Feature activation+1.37e+00

Pos logit contributions
interstitial+1.409
apult+1.374
anth+1.341
colored+1.332
 Title+1.281
Neg logit contributions
 contrace-1.978
 dstg-1.851
 Krishna-1.747
 Mississ-1.727
 Dru-1.721
Token report
Token ID989
Feature activation+7.43e-01

Pos logit contributions
interstitial+1.253
apult+1.246
anth+1.215
colored+1.200
 Title+1.154
Neg logit contributions
 contrace-0.915
 dstg-0.837
 Krishna-0.781
 Dru-0.768
 Mississ-0.764
Token Vietnamese
Token ID23618
Feature activation+4.05e-01

Pos logit contributions
interstitial+0.546
apult+0.534
anth+0.522
colored+0.519
 Title+0.505
Neg logit contributions
 contrace-0.632
 dstg-0.587
 Krishna-0.548
 Mississ-0.541
 Dru-0.538
Token airline
Token ID18091
Feature activation+2.00e+00

Pos logit contributions
interstitial+0.287
apult+0.282
anth+0.277
colored+0.274
 Title+0.269
Neg logit contributions
 contrace-0.349
 dstg-0.329
 Krishna-0.306
 Mississ-0.303
 Dru-0.300
Token takes
Token ID2753
Feature activation+1.27e+00

Pos logit contributions
interstitial+1.313
apult+1.291
anth+1.278
colored+1.266
 Title+1.234
Neg logit contributions
 contrace-1.840
 dstg-1.709
 Krishna-1.619
 Mississ-1.581
 Dru-1.576
Token steps
Token ID4831
Feature activation+4.94e+00

Pos logit contributions
interstitial+0.916
 Title+0.893
apult+0.884
colored+0.880
anth+0.873
Neg logit contributions
 contrace-1.073
 dstg-1.010
 Krishna-0.929
rists-0.909
 Mississ-0.907
Token to
Token ID284
Feature activation+1.40e+00

Pos logit contributions
interstitial+2.914
apult+2.903
anth+2.845
colored+2.785
 Title+2.777
Neg logit contributions
 contrace-4.795
 dstg-4.502
 Krishna-4.215
 Dru-4.163
 Mississ-4.134
Token open
Token ID1280
Feature activation+1.12e+00

Pos logit contributions
interstitial+0.959
apult+0.935
anth+0.921
colored+0.919
 Title+0.902
Neg logit contributions
 contrace-1.249
 dstg-1.167
 Krishna-1.088
 Mississ-1.070
 Dru-1.065
Token flights
Token ID13956
Feature activation+1.41e+00

Pos logit contributions
interstitial+0.873
apult+0.854
anth+0.837
colored+0.832
 Title+0.806
Neg logit contributions
 contrace-0.903
 dstg-0.837
 Krishna-0.782
 Mississ-0.771
 Dru-0.768
Token to
Token ID284
Feature activation+1.53e+00

Pos logit contributions
interstitial+1.031
apult+1.011
anth+0.987
colored+0.980
 Title+0.953
Neg logit contributions
 contrace-1.212
 dstg-1.126
 Krishna-1.053
 Mississ-1.038
 Dru-1.031
Token US
Token ID1294
Feature activation+1.37e+00

Pos logit contributions
interstitial+1.095
colored+1.055
apult+1.034
anth+1.027
 Title+1.008
Neg logit contributions
 contrace-1.351
 dstg-1.265
 Krishna-1.159
rists-1.143
 Mississ-1.132
Token(
Token ID7
Feature activation+7.21e-01

Pos logit contributions
 contrace+0.226
 dstg+0.206
 Krishna+0.193
 Mississ+0.190
 Dru+0.189
Neg logit contributions
interstitial-0.230
apult-0.225
anth-0.222
colored-0.220
 Title-0.214
Token5
Token ID20
Feature activation+2.18e+00

Pos logit contributions
interstitial+0.492
apult+0.480
anth+0.470
colored+0.467
 Title+0.450
Neg logit contributions
 contrace-0.651
 dstg-0.607
 Krishna-0.571
 Mississ-0.564
 Dru-0.562
Tokens
Token ID82
Feature activation+1.36e+00

Pos logit contributions
interstitial+1.728
anth+1.686
apult+1.684
colored+1.673
 Title+1.628
Neg logit contributions
 contrace-1.705
 dstg-1.559
 Krishna-1.464
 Mississ-1.445
 Dru-1.421
Token)}
Token ID38165
Feature activation+2.72e+00

Pos logit contributions
interstitial+0.856
apult+0.844
anth+0.830
colored+0.821
 Title+0.791
Neg logit contributions
 contrace-1.314
 dstg-1.199
 Krishna-1.140
 Mississ-1.130
 Dru-1.114
Token Kh
Token ID5311
Feature activation-2.14e-01

Pos logit contributions
interstitial+1.928
apult+1.875
colored+1.833
 Title+1.832
anth+1.830
Neg logit contributions
 contrace-2.372
 dstg-2.181
rists-2.006
 Mississ-1.998
 Krishna-1.990
Token7
Token ID22
Feature activation+3.47e+00

Pos logit contributions
 contrace+0.190
 dstg+0.177
 Krishna+0.166
 Mississ+0.164
 Dru+0.164
Neg logit contributions
interstitial-0.151
apult-0.147
anth-0.144
colored-0.143
 Title-0.138
Token {
Token ID1391
Feature activation+9.56e-01

Pos logit contributions
interstitial+2.286
apult+2.259
 Title+2.246
colored+2.229
anth+2.227
Neg logit contributions
 contrace-3.264
 dstg-2.925
 Mississ-2.702
rists-2.687
 Krishna-2.687
Token(
Token ID7
Feature activation+1.65e+00

Pos logit contributions
interstitial+0.737
apult+0.727
anth+0.720
colored+0.715
 Title+0.695
Neg logit contributions
 contrace-0.794
 dstg-0.707
 Krishna-0.661
 Mississ-0.654
 Dru-0.648
Token150
Token ID8628
Feature activation+5.36e-01

Pos logit contributions
interstitial+1.115
apult+1.088
anth+1.066
colored+1.059
 Title+1.024
Neg logit contributions
 contrace-1.499
 dstg-1.392
 Krishna-1.307
 Mississ-1.293
 Dru-1.286
Tokens
Token ID82
Feature activation+1.96e+00

Pos logit contributions
interstitial+0.428
apult+0.421
anth+0.421
colored+0.416
 Title+0.405
Neg logit contributions
 contrace-0.427
 dstg-0.381
 Krishna-0.357
 Mississ-0.351
 Dru-0.347
Token)}
Token ID38165
Feature activation+2.39e+00

Pos logit contributions
interstitial+1.205
apult+1.194
anth+1.176
colored+1.161
 Title+1.120
Neg logit contributions
 contrace-1.914
 dstg-1.734
 Krishna-1.651
 Mississ-1.641
 Dru-1.613
Token
Token ID239
Feature activation-8.62e-01

Pos logit contributions
interstitial+0.538
apult+0.524
anth+0.513
colored+0.510
 Title+0.490
Neg logit contributions
 contrace-0.797
 dstg-0.747
 Krishna-0.705
 Mississ-0.696
 Dru-0.695
Tokenм
Token ID43108
Feature activation+2.07e-01

Pos logit contributions
 contrace+0.755
 dstg+0.706
 Krishna+0.666
 Mississ+0.656
 Dru+0.655
Neg logit contributions
interstitial-0.607
apult-0.591
anth-0.578
colored-0.575
 Title-0.553
Tokenн
Token ID22177
Feature activation+6.22e-01

Pos logit contributions
interstitial+0.147
apult+0.143
anth+0.140
colored+0.139
 Title+0.134
Neg logit contributions
 contrace-0.181
 dstg-0.169
 Krishna-0.159
 Mississ-0.157
 Dru-0.157
Tokenи
Token ID18849
Feature activation+4.11e-01

Pos logit contributions
interstitial+0.444
apult+0.432
anth+0.422
colored+0.420
 Title+0.404
Neg logit contributions
 contrace-0.543
 dstg-0.506
 Krishna-0.476
 Mississ-0.469
 Dru-0.468
Tokenк
Token ID31583
Feature activation-7.95e-01

Pos logit contributions
interstitial+0.289
apult+0.281
anth+0.275
colored+0.273
 Title+0.262
Neg logit contributions
 contrace-0.362
 dstg-0.338
 Krishna-0.319
 Mississ-0.314
 Dru-0.314
Tokenо�
Token ID25443
Feature activation+3.16e+00

Pos logit contributions
 contrace+0.685
 dstg+0.640
 Krishna+0.603
 Mississ+0.595
 Dru+0.595
Neg logit contributions
interstitial-0.574
apult-0.555
anth-0.543
colored-0.542
 Title-0.519
Token
Token ID110
Feature activation+3.04e+00

Pos logit contributions
interstitial+1.310
apult+1.284
anth+1.233
colored+1.227
 Title+1.157
Neg logit contributions
 contrace-3.668
 dstg-3.477
 Krishna-3.324
 Mississ-3.291
 Dru-3.283
Token
Token ID220
Feature activation+2.61e+00

Pos logit contributions
interstitial+1.926
apult+1.897
anth+1.855
colored+1.830
 Title+1.783
Neg logit contributions
 contrace-2.878
 dstg-2.692
 Krishna-2.531
 Mississ-2.508
 Dru-2.488
Token
Token ID141
Feature activation+1.90e+00

Pos logit contributions
interstitial+1.638
apult+1.602
anth+1.562
colored+1.548
 Title+1.488
Neg logit contributions
 contrace-2.500
 dstg-2.333
 Krishna-2.203
 Mississ-2.183
 Dru-2.174
Token
Token ID227
Feature activation-1.15e+00

Pos logit contributions
interstitial+1.142
apult+1.109
anth+1.084
colored+1.075
 Title+1.035
Neg logit contributions
 contrace-1.871
 dstg-1.761
 Krishna-1.659
 Mississ-1.651
 Dru-1.637
Tokenа
Token ID16142
Feature activation+1.11e-01

Pos logit contributions
 contrace+0.929
 dstg+0.863
 Krishna+0.810
 Mississ+0.799
 Dru+0.798
Neg logit contributions
interstitial-0.889
apult-0.866
anth-0.846
colored-0.844
 Title-0.810
Token)
Token ID8
Feature activation-8.66e-01

Pos logit contributions
 contrace+1.311
 dstg+1.214
 Krishna+1.131
 Mississ+1.112
 Dru+1.109
Neg logit contributions
interstitial-1.411
apult-1.378
anth-1.353
colored-1.346
 Title-1.299
Token and
Token ID290
Feature activation-8.35e-01

Pos logit contributions
 contrace+0.721
 dstg+0.669
 Krishna+0.627
 Mississ+0.619
 Dru+0.616
Neg logit contributions
interstitial-0.651
apult-0.637
anth-0.624
colored-0.620
 Title-0.600
Token obesity
Token ID13825
Feature activation-7.89e-01

Pos logit contributions
 contrace+0.717
 dstg+0.667
 Krishna+0.627
 Mississ+0.619
 Dru+0.617
Neg logit contributions
interstitial-0.607
apult-0.593
anth-0.580
colored-0.577
 Title-0.555
Token/
Token ID14
Feature activation+6.88e-01

Pos logit contributions
 contrace+0.645
 dstg+0.598
 Krishna+0.560
 Mississ+0.552
 Dru+0.550
Neg logit contributions
interstitial-0.606
apult-0.593
anth-0.581
colored-0.577
 Title-0.558
Tokenover
Token ID2502
Feature activation+1.36e+00

Pos logit contributions
interstitial+0.499
apult+0.486
anth+0.478
colored+0.474
 Title+0.457
Neg logit contributions
 contrace-0.596
 dstg-0.553
 Krishna-0.520
 Mississ-0.514
 Dru-0.511
Tokenweight
Token ID6551
Feature activation+3.46e+00

Pos logit contributions
interstitial+0.640
apult+0.622
anth+0.607
colored+0.601
 Title+0.568
Neg logit contributions
 contrace-1.514
 dstg-1.432
 Krishna-1.360
 Mississ-1.352
 Dru-1.342
Token trends
Token ID11257
Feature activation+1.16e-02

Pos logit contributions
interstitial+2.291
apult+2.231
anth+2.210
colored+2.183
 Title+2.164
Neg logit contributions
 contrace-3.148
 dstg-2.946
 Krishna-2.742
 Mississ-2.719
 Dru-2.695
Token in
Token ID287
Feature activation+7.29e-02

Pos logit contributions
interstitial+0.009
apult+0.009
anth+0.009
colored+0.008
 Title+0.008
Neg logit contributions
 contrace-0.009
 dstg-0.009
 Krishna-0.008
 Mississ-0.008
 Dru-0.008
Token all
Token ID477
Feature activation-8.98e-01

Pos logit contributions
interstitial+0.052
apult+0.051
anth+0.050
colored+0.050
 Title+0.048
Neg logit contributions
 contrace-0.063
 dstg-0.059
 Krishna-0.055
 Mississ-0.054
 Dru-0.054
Token 53
Token ID7192
Feature activation-7.26e-02

Pos logit contributions
 contrace+0.853
 dstg+0.800
 Krishna+0.757
 Mississ+0.748
 Dru+0.745
Neg logit contributions
interstitial-0.571
apult-0.556
anth-0.542
colored-0.538
 Title-0.516
Token of
Token ID286
Feature activation-8.01e-01

Pos logit contributions
 contrace+0.063
 dstg+0.059
 Krishna+0.056
 Mississ+0.055
 Dru+0.055
Neg logit contributions
interstitial-0.052
apult-0.051
anth-0.049
colored-0.049
 Title-0.047
Token:
Token ID25
Feature activation+3.10e-01

Pos logit contributions
interstitial+0.101
apult+0.099
anth+0.098
colored+0.097
 Title+0.094
Neg logit contributions
 contrace-0.105
 dstg-0.097
 Krishna-0.091
 Mississ-0.090
 Dru-0.089
Token<|endoftext|>
Token ID50256
Feature activation+7.84e-01

Pos logit contributions
interstitial+0.178
apult+0.173
anth+0.169
colored+0.167
 Title+0.161
Neg logit contributions
 contrace-0.313
 dstg-0.295
 Krishna-0.279
 Mississ-0.276
 Dru-0.275
TokenCourt
Token ID36699
Feature activation-9.64e-01

Pos logit contributions
interstitial+0.553
apult+0.538
anth+0.530
colored+0.526
 Title+0.505
Neg logit contributions
 contrace-0.694
 dstg-0.644
 Krishna-0.607
 Mississ-0.599
 Dru-0.598
Token documents
Token ID4963
Feature activation+1.97e-01

Pos logit contributions
 contrace+0.817
 dstg+0.759
 Krishna+0.714
 Mississ+0.706
 Dru+0.704
Neg logit contributions
interstitial-0.713
apult-0.692
anth-0.678
colored-0.675
 Title-0.648
Token reveals
Token ID10069
Feature activation+4.64e-01

Pos logit contributions
interstitial+0.151
apult+0.147
anth+0.144
colored+0.143
 Title+0.138
Neg logit contributions
 contrace-0.162
 dstg-0.150
 Krishna-0.141
 Mississ-0.139
 Dru-0.139
Token Bungie
Token ID47593
Feature activation+3.90e+00

Pos logit contributions
interstitial+0.339
apult+0.331
anth+0.325
colored+0.322
 Title+0.313
Neg logit contributions
 contrace-0.396
 dstg-0.368
 Krishna-0.344
 Mississ-0.339
 Dru-0.338
Token's
Token ID338
Feature activation-3.26e-01

Pos logit contributions
interstitial+3.014
apult+2.986
colored+2.932
anth+2.913
 Title+2.911
Neg logit contributions
 contrace-3.050
 dstg-2.863
 Krishna-2.620
rists-2.573
 Mississ-2.559
Token plans
Token ID3352
Feature activation-3.85e-02

Pos logit contributions
 contrace+0.270
 dstg+0.251
 Krishna+0.235
 Mississ+0.232
 Dru+0.231
Neg logit contributions
interstitial-0.246
apult-0.240
anth-0.235
colored-0.234
 Title-0.226
Token for
Token ID329
Feature activation+7.52e-01

Pos logit contributions
 contrace+0.033
 dstg+0.030
 Krishna+0.028
 Mississ+0.028
 Dru+0.028
Neg logit contributions
interstitial-0.029
apult-0.028
anth-0.027
colored-0.027
 Title-0.026
Token Destiny
Token ID17886
Feature activation+1.64e+00

Pos logit contributions
interstitial+0.557
apult+0.545
anth+0.534
colored+0.531
 Title+0.515
Neg logit contributions
 contrace-0.634
 dstg-0.590
 Krishna-0.552
 Mississ-0.544
 Dru-0.541
Token,
Token ID11
Feature activation-5.79e-01

Pos logit contributions
interstitial+1.162
apult+1.137
anth+1.113
colored+1.105
 Title+1.072
Neg logit contributions
 contrace-1.428
 dstg-1.332
 Krishna-1.251
 Mississ-1.235
 Dru-1.228
Token doesn
Token ID1595
Feature activation-2.29e-01

Pos logit contributions
 contrace+1.089
 dstg+1.009
 Krishna+0.950
 Mississ+0.936
 Dru+0.933
Neg logit contributions
interstitial-1.003
apult-0.979
anth-0.958
colored-0.952
 Title-0.919
Token
Token ID447
Feature activation-8.41e-01

Pos logit contributions
 contrace+0.201
 dstg+0.191
 Krishna+0.180
 Mississ+0.178
 Dru+0.178
Neg logit contributions
interstitial-0.159
apult-0.155
anth-0.150
colored-0.149
 Title-0.143
Token
Token ID247
Feature activation+4.29e-01

Pos logit contributions
 contrace+0.799
 dstg+0.756
 Krishna+0.722
 Mississ+0.704
 Dru+0.704
Neg logit contributions
interstitial-0.516
apult-0.511
anth-0.500
colored-0.485
 Title-0.466
Tokent
Token ID83
Feature activation+3.68e-01

Pos logit contributions
interstitial+0.278
apult+0.271
anth+0.265
colored+0.263
 Title+0.253
Neg logit contributions
 contrace-0.402
 dstg-0.376
 Krishna-0.355
 Mississ-0.351
 Dru-0.350
Token have
Token ID423
Feature activation+3.73e-01

Pos logit contributions
interstitial+0.262
apult+0.257
anth+0.254
colored+0.251
 Title+0.244
Neg logit contributions
 contrace-0.316
 dstg-0.295
 Krishna-0.277
 Mississ-0.273
 Dru-0.272
Token layers
Token ID11685
Feature activation+7.69e-01

Pos logit contributions
interstitial+0.278
apult+0.272
anth+0.267
colored+0.265
 Title+0.257
Neg logit contributions
 contrace-0.313
 dstg-0.291
 Krishna-0.272
 Mississ-0.269
 Dru-0.268
Token.
Token ID13
Feature activation-4.06e-01

Pos logit contributions
interstitial+0.549
apult+0.538
anth+0.527
colored+0.524
 Title+0.505
Neg logit contributions
 contrace-0.669
 dstg-0.622
 Krishna-0.584
 Mississ-0.578
 Dru-0.574
Token He
Token ID679
Feature activation-1.26e+00

Pos logit contributions
 contrace+0.338
 dstg+0.315
 Krishna+0.296
 Mississ+0.292
 Dru+0.291
Neg logit contributions
interstitial-0.306
apult-0.298
anth-0.291
colored-0.290
 Title-0.279
Token doesn
Token ID1595
Feature activation-1.04e+00

Pos logit contributions
 contrace+0.923
 dstg+0.847
 Krishna+0.787
 Mississ+0.775
 Dru+0.771
Neg logit contributions
interstitial-1.072
apult-1.049
anth-1.028
colored-1.024
 Title-0.994
Token
Token ID447
Feature activation-4.71e-01

Pos logit contributions
 contrace+0.980
 dstg+0.946
 Krishna+0.894
 Mississ+0.886
 Dru+0.883
Neg logit contributions
interstitial-0.651
apult-0.629
anth-0.604
colored-0.602
 Title-0.575
Token
Token ID247
Feature activation+2.33e-01

Pos logit contributions
 contrace+0.456
 dstg+0.432
 Krishna+0.412
 Dru+0.403
 Mississ+0.403
Neg logit contributions
interstitial-0.282
apult-0.278
anth-0.271
colored-0.265
 Title-0.255
Token for
Token ID329
Feature activation+7.58e-01

Pos logit contributions
interstitial+0.295
apult+0.287
anth+0.280
colored+0.279
 Title+0.269
Neg logit contributions
 contrace-0.356
 dstg-0.331
 Krishna-0.313
 Mississ-0.309
 Dru-0.307
Token all
Token ID477
Feature activation+7.28e-01

Pos logit contributions
interstitial+0.553
apult+0.540
anth+0.528
colored+0.525
 Title+0.507
Neg logit contributions
 contrace-0.649
 dstg-0.604
 Krishna-0.567
 Mississ-0.560
 Dru-0.558
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
interstitial+0.548
apult+0.537
anth+0.526
colored+0.522
 Title+0.506
Neg logit contributions
 contrace-0.604
 dstg-0.561
 Krishna-0.524
 Mississ-0.517
 Dru-0.515
Token new
Token ID649
Feature activation+1.11e-01

Pos logit contributions
interstitial+0.891
apult+0.876
anth+0.859
colored+0.852
 Title+0.830
Neg logit contributions
 contrace-0.929
 dstg-0.860
 Krishna-0.802
 Mississ-0.788
 Dru-0.786
Token signings
Token ID42113
Feature activation+5.71e-01

Pos logit contributions
interstitial+0.087
apult+0.085
anth+0.083
colored+0.083
 Title+0.080
Neg logit contributions
 contrace-0.089
 dstg-0.082
 Krishna-0.077
 Mississ-0.076
 Dru-0.075
Token to
Token ID284
Feature activation+9.53e-01

Pos logit contributions
interstitial+0.418
apult+0.408
anth+0.400
colored+0.398
 Title+0.384
Neg logit contributions
 contrace-0.488
 dstg-0.454
 Krishna-0.426
 Mississ-0.421
 Dru-0.419
Token start
Token ID923
Feature activation+8.08e-01

Pos logit contributions
interstitial+0.699
apult+0.685
anth+0.672
colored+0.666
 Title+0.645
Neg logit contributions
 contrace-0.810
 dstg-0.753
 Krishna-0.705
 Mississ-0.696
 Dru-0.694
Token contributing
Token ID14329
Feature activation+1.69e+00

Pos logit contributions
interstitial+0.609
apult+0.597
anth+0.586
colored+0.581
 Title+0.563
Neg logit contributions
 contrace-0.671
 dstg-0.623
 Krishna-0.583
 Mississ-0.575
 Dru-0.572
Token right
Token ID826
Feature activation-9.90e-01

Pos logit contributions
interstitial+1.208
apult+1.188
anth+1.165
colored+1.152
 Title+1.120
Neg logit contributions
 contrace-1.468
 dstg-1.369
 Krishna-1.281
 Mississ-1.265
 Dru-1.259
Token away
Token ID1497
Feature activation-5.03e-02

Pos logit contributions
 contrace+0.732
 dstg+0.673
 Krishna+0.629
 Mississ+0.618
 Dru+0.615
Neg logit contributions
interstitial-0.838
apult-0.817
anth-0.800
colored-0.799
 Title-0.772
Token,
Token ID11
Feature activation+2.93e-03

Pos logit contributions
 contrace+0.042
 dstg+0.039
 Krishna+0.036
 Mississ+0.036
 Dru+0.036
Neg logit contributions
interstitial-0.038
apult-0.037
anth-0.037
colored-0.036
 Title-0.035
Token Aram
Token ID39026
Feature activation+7.15e-01

Pos logit contributions
interstitial+0.433
apult+0.423
anth+0.415
colored+0.412
 Title+0.399
Neg logit contributions
 contrace-0.505
 dstg-0.470
 Krishna-0.440
 Mississ-0.435
 Dru-0.432
Token Sar
Token ID6866
Feature activation+1.37e+00

Pos logit contributions
interstitial+0.446
apult+0.434
anth+0.424
colored+0.420
 Title+0.403
Neg logit contributions
 contrace-0.686
 dstg-0.644
 Krishna-0.609
 Mississ-0.602
 Dru-0.600
Tokenoy
Token ID726
Feature activation-1.13e+00

Pos logit contributions
interstitial+0.906
apult+0.889
anth+0.875
colored+0.861
 Title+0.826
Neg logit contributions
 contrace-1.268
 dstg-1.184
 Krishna-1.111
 Mississ-1.102
 Dru-1.098
Tokenan
Token ID272
Feature activation+7.09e-01

Pos logit contributions
 contrace+1.068
 dstg+1.001
 Krishna+0.949
 Mississ+0.937
 Dru+0.934
Neg logit contributions
interstitial-0.715
apult-0.695
anth-0.677
colored-0.674
 Title-0.646
Token
Token ID447
Feature activation-6.55e-01

Pos logit contributions
interstitial+0.546
apult+0.536
anth+0.527
colored+0.522
 Title+0.506
Neg logit contributions
 contrace-0.577
 dstg-0.536
 Krishna-0.498
 Mississ-0.492
 Dru-0.489
Token
Token ID247
Feature activation+3.02e-01

Pos logit contributions
 contrace+0.647
 dstg+0.608
 Krishna+0.580
 Mississ+0.570
 Dru+0.570
Neg logit contributions
interstitial-0.387
apult-0.379
anth-0.369
colored-0.363
 Title-0.347
Tokens
Token ID82
Feature activation+4.16e-01

Pos logit contributions
interstitial+0.241
apult+0.235
anth+0.233
colored+0.230
 Title+0.224
Neg logit contributions
 contrace-0.238
 dstg-0.219
 Krishna-0.203
 Mississ-0.201
 Dru-0.200
Token
Token ID564
Feature activation-1.69e+00

Pos logit contributions
interstitial+0.302
apult+0.295
anth+0.289
colored+0.287
 Title+0.277
Neg logit contributions
 contrace-0.358
 dstg-0.333
 Krishna-0.312
 Mississ-0.308
 Dru-0.307
Token
Token ID250
Feature activation-3.40e-01

Pos logit contributions
 contrace+1.604
 dstg+1.502
 Krishna+1.434
 Dru+1.403
 Mississ+1.402
Neg logit contributions
interstitial-1.057
apult-1.038
anth-1.011
colored-0.995
 Title-0.956
Tokenoxy
Token ID23536
Feature activation-1.20e+00

Pos logit contributions
 contrace+0.304
 dstg+0.284
 Krishna+0.267
 Mississ+0.264
 Dru+0.263
Neg logit contributions
interstitial-0.235
apult-0.229
anth-0.224
colored-0.223
 Title-0.215
Tokengen
Token ID5235
Feature activation-1.93e-01

Pos logit contributions
 contrace+1.036
 dstg+0.966
 Krishna+0.911
 Mississ+0.898
 Dru+0.896
Neg logit contributions
interstitial-0.861
apult-0.840
anth-0.817
colored-0.813
 Title-0.785
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
interstitial+0.278
apult+0.268
anth+0.260
colored+0.258
 Title+0.244
Neg logit contributions
 contrace-0.503
 dstg-0.480
 Krishna-0.456
 Mississ-0.451
 Dru-0.450
TokenRomney
Token ID42184
Feature activation+1.19e+00

Pos logit contributions
interstitial+0.336
apult+0.328
anth+0.322
colored+0.320
 Title+0.308
Neg logit contributions
 contrace-0.441
 dstg-0.409
 Krishna-0.385
 Mississ-0.381
 Dru-0.379
Token was
Token ID373
Feature activation+3.22e-01

Pos logit contributions
interstitial+0.921
apult+0.912
anth+0.893
colored+0.889
 Title+0.866
Neg logit contributions
 contrace-0.951
 dstg-0.890
 Krishna-0.819
 Mississ-0.811
 Dru-0.799
Token obviously
Token ID6189
Feature activation+1.28e+00

Pos logit contributions
interstitial+0.241
apult+0.237
anth+0.231
colored+0.231
 Title+0.225
Neg logit contributions
 contrace-0.267
 dstg-0.249
 Krishna-0.231
 Mississ-0.228
 Dru-0.226
Token more
Token ID517
Feature activation+2.08e-01

Pos logit contributions
interstitial+0.933
apult+0.928
colored+0.904
anth+0.899
 Title+0.889
Neg logit contributions
 contrace-1.062
 dstg-0.996
 Krishna-0.920
 Mississ-0.909
rists-0.903
Token closely
Token ID7173
Feature activation+1.25e+00

Pos logit contributions
interstitial+0.154
apult+0.152
colored+0.148
anth+0.148
 Title+0.144
Neg logit contributions
 contrace-0.174
 dstg-0.163
 Krishna-0.151
 Mississ-0.149
 Dru-0.148
Token associated
Token ID3917
Feature activation+6.28e-01

Pos logit contributions
interstitial+0.825
apult+0.807
colored+0.790
anth+0.778
 Title+0.765
Neg logit contributions
 contrace-1.151
 dstg-1.084
 Krishna-1.010
 Mississ-0.993
rists-0.988
Token with
Token ID351
Feature activation+1.68e+00

Pos logit contributions
interstitial+0.451
apult+0.443
anth+0.433
colored+0.431
 Title+0.417
Neg logit contributions
 contrace-0.541
 dstg-0.504
 Krishna-0.474
 Mississ-0.468
 Dru-0.465
Token Bain
Token ID33126
Feature activation+9.44e-01

Pos logit contributions
interstitial+1.111
apult+1.086
anth+1.058
colored+1.055
 Title+1.023
Neg logit contributions
 contrace-1.540
 dstg-1.446
 Krishna-1.353
 Mississ-1.339
 Dru-1.327
Token Capital
Token ID9747
Feature activation+1.00e+00

Pos logit contributions
interstitial+0.636
apult+0.631
anth+0.615
colored+0.614
 Title+0.592
Neg logit contributions
 contrace-0.851
 dstg-0.796
 Krishna-0.747
 Mississ-0.740
 Dru-0.733
Token than
Token ID621
Feature activation+2.51e-01

Pos logit contributions
interstitial+0.727
apult+0.720
anth+0.701
colored+0.700
 Title+0.679
Neg logit contributions
 contrace-0.851
 dstg-0.792
 Krishna-0.742
 Mississ-0.731
 Dru-0.726
Token and
Token ID290
Feature activation+2.91e-01

Pos logit contributions
 contrace+0.121
 dstg+0.113
 Krishna+0.106
 Mississ+0.105
 Dru+0.104
Neg logit contributions
interstitial-0.103
apult-0.100
anth-0.098
colored-0.098
 Title-0.094
Token it
Token ID340
Feature activation+6.83e-01

Pos logit contributions
interstitial+0.219
apult+0.214
anth+0.210
colored+0.209
 Title+0.203
Neg logit contributions
 contrace-0.242
 dstg-0.224
 Krishna-0.210
 Mississ-0.207
 Dru-0.206
Token was
Token ID373
Feature activation-2.37e-01

Pos logit contributions
interstitial+0.510
apult+0.499
anth+0.489
colored+0.486
 Title+0.469
Neg logit contributions
 contrace-0.571
 dstg-0.531
 Krishna-0.498
 Mississ-0.491
 Dru-0.489
Token everywhere
Token ID8347
Feature activation+1.06e-01

Pos logit contributions
 contrace+0.190
 dstg+0.177
 Krishna+0.164
 Mississ+0.162
 Dru+0.161
Neg logit contributions
interstitial-0.185
apult-0.181
anth-0.177
colored-0.177
 Title-0.171
Token.
Token ID13
Feature activation-4.96e-01

Pos logit contributions
interstitial+0.081
apult+0.080
anth+0.078
colored+0.078
 Title+0.075
Neg logit contributions
 contrace-0.086
 dstg-0.080
 Krishna-0.075
 Mississ-0.073
 Dru-0.073
Token
Token ID198
Feature activation-1.42e-01

Pos logit contributions
 contrace+0.464
 dstg+0.436
 Krishna+0.413
 Mississ+0.409
 Dru+0.408
Neg logit contributions
interstitial-0.322
apult-0.313
anth-0.305
colored-0.304
 Title-0.289
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
 contrace+0.141
 dstg+0.136
 Krishna+0.129
 Mississ+0.128
 Dru+0.128
Neg logit contributions
interstitial-0.083
apult-0.080
anth-0.077
colored-0.076
 Title-0.072
TokenTHE
Token ID10970
Feature activation-3.69e-02

Pos logit contributions
interstitial+0.077
apult+0.075
anth+0.073
colored+0.073
 Title+0.070
Neg logit contributions
 contrace-0.100
 dstg-0.093
 Krishna-0.088
 Mississ-0.087
 Dru-0.086
Token PUR
Token ID33079
Feature activation+1.20e+00

Pos logit contributions
 contrace+0.035
 dstg+0.032
 Krishna+0.031
 Mississ+0.030
 Dru+0.030
Neg logit contributions
interstitial-0.024
apult-0.023
anth-0.022
colored-0.022
 Title-0.021
TokenGE
Token ID8264
Feature activation-1.47e-02

Pos logit contributions
interstitial+0.758
apult+0.741
anth+0.722
colored+0.719
 Title+0.693
Neg logit contributions
 contrace-1.137
 dstg-1.064
 Krishna-1.003
 Mississ-0.992
 Dru-0.988
Token D
Token ID360
Feature activation-5.55e-01

Pos logit contributions
 contrace+0.013
 dstg+0.012
 Krishna+0.012
 Mississ+0.012
 Dru+0.012
Neg logit contributions
interstitial-0.010
apult-0.010
anth-0.010
colored-0.009
 Title-0.009
Token to
Token ID284
Feature activation+8.60e-02

Pos logit contributions
 contrace+0.027
 dstg+0.025
 Krishna+0.023
 Mississ+0.023
 Dru+0.023
Neg logit contributions
interstitial-0.019
apult-0.019
anth-0.019
colored-0.018
 Title-0.018
Token "
Token ID366
Feature activation+3.39e-02

Pos logit contributions
interstitial+0.061
apult+0.060
anth+0.059
colored+0.058
 Title+0.057
Neg logit contributions
 contrace-0.075
 dstg-0.070
 Krishna-0.065
 Mississ-0.065
 Dru-0.064
Tokensky
Token ID15688
Feature activation+7.44e-01

Pos logit contributions
interstitial+0.023
apult+0.023
anth+0.022
colored+0.022
 Title+0.021
Neg logit contributions
 contrace-0.031
 dstg-0.029
 Krishna-0.027
 Mississ-0.027
 Dru-0.026
Tokenrocket
Token ID30431
Feature activation-6.37e-01

Pos logit contributions
interstitial+0.617
apult+0.601
anth+0.591
colored+0.588
 Title+0.570
Neg logit contributions
 contrace-0.564
 dstg-0.519
 Krishna-0.483
 Mississ-0.476
 Dru-0.475
Token,"
Token ID553
Feature activation-1.73e-01

Pos logit contributions
 contrace+0.495
 dstg+0.457
 Krishna+0.427
 Mississ+0.420
 Dru+0.420
Neg logit contributions
interstitial-0.516
apult-0.502
anth-0.493
colored-0.491
 Title-0.474
Token and
Token ID290
Feature activation-7.54e-01

Pos logit contributions
 contrace+0.146
 dstg+0.136
 Krishna+0.128
 Mississ+0.126
 Dru+0.126
Neg logit contributions
interstitial-0.127
apult-0.124
anth-0.122
colored-0.121
 Title-0.117
Token his
Token ID465
Feature activation+1.30e-01

Pos logit contributions
 contrace+0.609
 dstg+0.564
 Krishna+0.527
 Mississ+0.520
 Dru+0.518
Neg logit contributions
interstitial-0.586
apult-0.574
anth-0.563
colored-0.559
 Title-0.541
Token recent
Token ID2274
Feature activation-2.66e-01

Pos logit contributions
interstitial+0.096
apult+0.095
anth+0.093
colored+0.092
 Title+0.090
Neg logit contributions
 contrace-0.109
 dstg-0.102
 Krishna-0.095
 Mississ-0.094
 Dru-0.094
Token town
Token ID3240
Feature activation-9.84e-01

Pos logit contributions
 contrace+0.221
 dstg+0.205
 Krishna+0.192
 Mississ+0.189
 Dru+0.189
Neg logit contributions
interstitial-0.200
apult-0.196
anth-0.192
colored-0.191
 Title-0.185
Token-
Token ID12
Feature activation-1.57e-01

Pos logit contributions
 contrace+0.900
 dstg+0.834
 Krishna+0.795
 Mississ+0.784
 Dru+0.777
Neg logit contributions
interstitial-0.660
apult-0.646
anth-0.629
colored-0.616
 Title-0.591
Tokenhall
Token ID18323
Feature activation-6.05e-01

Pos logit contributions
 contrace+0.153
 dstg+0.144
 Krishna+0.137
 Mississ+0.135
 Dru+0.135
Neg logit contributions
interstitial-0.095
apult-0.093
anth-0.090
colored-0.089
 Title-0.086
Tokenness
Token ID1108
Feature activation-5.29e-01

Pos logit contributions
 contrace+0.841
 dstg+0.780
 Krishna+0.728
 Dru+0.722
 Mississ+0.720
Neg logit contributions
interstitial-0.802
apult-0.783
anth-0.765
colored-0.759
 Title-0.733
Token and
Token ID290
Feature activation-7.28e-01

Pos logit contributions
 contrace+0.455
 dstg+0.424
 Krishna+0.397
 Mississ+0.393
 Dru+0.390
Neg logit contributions
interstitial-0.383
apult-0.374
anth-0.367
colored-0.364
 Title-0.352
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
 contrace+0.621
 dstg+0.581
 Krishna+0.542
 Mississ+0.535
 Dru+0.531
Neg logit contributions
interstitial-0.531
apult-0.519
anth-0.509
colored-0.506
 Title-0.491
Token historian
Token ID18026
Feature activation+3.32e-01

Pos logit contributions
 contrace+0.111
 dstg+0.103
 Krishna+0.096
 Mississ+0.095
 Dru+0.094
Neg logit contributions
interstitial-0.100
apult-0.098
anth-0.096
colored-0.095
 Title-0.092
Token of
Token ID286
Feature activation+4.21e-01

Pos logit contributions
interstitial+0.237
apult+0.231
anth+0.226
colored+0.225
 Title+0.217
Neg logit contributions
 contrace-0.290
 dstg-0.270
 Krishna-0.254
 Mississ-0.251
 Dru-0.249
Token culture
Token ID3968
Feature activation-4.29e-01

Pos logit contributions
interstitial+0.301
apult+0.294
anth+0.289
colored+0.287
 Title+0.279
Neg logit contributions
 contrace-0.366
 dstg-0.342
 Krishna-0.318
 Mississ-0.314
 Dru-0.312
Token,
Token ID11
Feature activation-8.12e-01

Pos logit contributions
 contrace+0.367
 dstg+0.341
 Krishna+0.320
 Mississ+0.316
 Dru+0.315
Neg logit contributions
interstitial-0.313
apult-0.306
anth-0.300
colored-0.298
 Title-0.288
Token he
Token ID339
Feature activation+1.44e-01

Pos logit contributions
 contrace+0.600
 dstg+0.552
 Krishna+0.515
 Mississ+0.507
 Dru+0.505
Neg logit contributions
interstitial-0.686
apult-0.672
anth-0.659
colored-0.656
 Title-0.636
Token summed
Token ID32794
Feature activation-7.52e-01

Pos logit contributions
interstitial+0.112
apult+0.110
anth+0.108
colored+0.107
 Title+0.103
Neg logit contributions
 contrace-0.116
 dstg-0.108
 Krishna-0.100
 Mississ-0.099
 Dru-0.098
Token up
Token ID510
Feature activation-1.99e-01

Pos logit contributions
 contrace+0.722
 dstg+0.677
 Krishna+0.645
 Mississ+0.636
 Dru+0.635
Neg logit contributions
interstitial-0.467
apult-0.455
anth-0.443
colored-0.440
 Title-0.421
Token Z
Token ID1168
Feature activation+3.71e-01

Pos logit contributions
 contrace+0.163
 dstg+0.151
 Krishna+0.141
 Mississ+0.139
 Dru+0.138
Neg logit contributions
interstitial-0.153
apult-0.149
anth-0.147
colored-0.146
 Title-0.141
Token to
Token ID284
Feature activation-8.46e-01

Pos logit contributions
 contrace+0.040
 dstg+0.037
 Krishna+0.035
 Mississ+0.034
 Dru+0.034
Neg logit contributions
interstitial-0.032
apult-0.031
anth-0.030
colored-0.030
 Title-0.029
Token be
Token ID307
Feature activation-1.34e-01

Pos logit contributions
 contrace+0.702
 dstg+0.652
 Krishna+0.612
 Mississ+0.605
 Dru+0.601
Neg logit contributions
interstitial-0.641
apult-0.623
anth-0.610
colored-0.607
 Title-0.585
Token,
Token ID11
Feature activation-5.86e-01

Pos logit contributions
 contrace+0.111
 dstg+0.103
 Krishna+0.097
 Mississ+0.095
 Dru+0.095
Neg logit contributions
interstitial-0.101
apult-0.099
anth-0.097
colored-0.097
 Title-0.094
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
 contrace+0.500
 dstg+0.462
 Krishna+0.439
 Mississ+0.433
 Dru+0.431
Neg logit contributions
interstitial-0.433
apult-0.422
anth-0.411
colored-0.408
 Title-0.391
Token I
Token ID314
Feature activation-3.36e-01

Pos logit contributions
 contrace+0.417
 dstg+0.391
 Krishna+0.368
 Mississ+0.364
 Dru+0.363
Neg logit contributions
interstitial-0.302
apult-0.294
anth-0.288
colored-0.285
 Title-0.276
Token knew
Token ID2993
Feature activation-1.73e+00

Pos logit contributions
 contrace+0.283
 dstg+0.266
 Krishna+0.247
 Mississ+0.244
 Dru+0.243
Neg logit contributions
interstitial-0.247
apult-0.243
anth-0.238
colored-0.237
 Title-0.229
Token my
Token ID616
Feature activation-3.88e-01

Pos logit contributions
 contrace+1.550
 dstg+1.438
 Krishna+1.367
 Mississ+1.350
 Dru+1.346
Neg logit contributions
interstitial-1.195
apult-1.165
anth-1.135
colored-1.130
 Title-1.076
Token husband
Token ID5229
Feature activation-5.45e-01

Pos logit contributions
 contrace+0.319
 dstg+0.297
 Krishna+0.277
 Mississ+0.274
 Dru+0.273
Neg logit contributions
interstitial-0.295
apult-0.288
anth-0.283
colored-0.281
 Title-0.272
Token was
Token ID373
Feature activation+2.44e-01

Pos logit contributions
 contrace+0.480
 dstg+0.451
 Krishna+0.421
 Mississ+0.416
 Dru+0.414
Neg logit contributions
interstitial-0.380
apult-0.372
anth-0.365
colored-0.362
 Title-0.351
Token doing
Token ID1804
Feature activation+4.90e-01

Pos logit contributions
interstitial+0.180
apult+0.176
anth+0.174
colored+0.173
 Title+0.170
Neg logit contributions
 contrace-0.203
 dstg-0.192
 Krishna-0.177
 Mississ-0.175
 Dru-0.174
Token this
Token ID428
Feature activation-7.26e-01

Pos logit contributions
interstitial+0.358
apult+0.349
anth+0.343
colored+0.341
 Title+0.333
Neg logit contributions
 contrace-0.415
 dstg-0.389
 Krishna-0.362
 Mississ-0.358
 Dru-0.356
Token Wall
Token ID5007
Feature activation-5.11e-01

Pos logit contributions
interstitial+0.260
apult+0.256
anth+0.253
colored+0.251
 Title+0.247
Neg logit contributions
 contrace-0.190
 dstg-0.172
 Krishna-0.158
 Mississ-0.155
 Dru-0.154
Token Street
Token ID3530
Feature activation+2.63e-01

Pos logit contributions
 contrace+0.462
 dstg+0.434
 Krishna+0.410
 Mississ+0.405
 Dru+0.404
Neg logit contributions
interstitial-0.347
apult-0.337
anth-0.329
colored-0.327
 Title-0.313
Token,
Token ID11
Feature activation-2.33e-01

Pos logit contributions
interstitial+0.199
apult+0.195
anth+0.191
colored+0.190
 Title+0.184
Neg logit contributions
 contrace-0.218
 dstg-0.202
 Krishna-0.190
 Mississ-0.187
 Dru-0.186
Token or
Token ID393
Feature activation+1.25e+00

Pos logit contributions
 contrace+0.197
 dstg+0.183
 Krishna+0.171
 Mississ+0.169
 Dru+0.168
Neg logit contributions
interstitial-0.173
apult-0.169
anth-0.166
colored-0.165
 Title-0.159
Token whether
Token ID1771
Feature activation+1.57e+00

Pos logit contributions
interstitial+0.910
apult+0.897
anth+0.883
colored+0.872
 Title+0.858
Neg logit contributions
 contrace-1.051
 dstg-0.981
 Krishna-0.913
 Mississ-0.901
 Dru-0.894
Token Wall
Token ID5007
Feature activation-4.61e-01

Pos logit contributions
interstitial+1.145
apult+1.123
anth+1.104
colored+1.095
 Title+1.071
Neg logit contributions
 contrace-1.328
 dstg-1.238
 Krishna-1.155
 Mississ-1.137
 Dru-1.131
Token Street
Token ID3530
Feature activation+4.43e-01

Pos logit contributions
 contrace+0.420
 dstg+0.394
 Krishna+0.372
 Mississ+0.367
 Dru+0.366
Neg logit contributions
interstitial-0.309
apult-0.301
anth-0.294
colored-0.292
 Title-0.281
Token will
Token ID481
Feature activation+1.08e+00

Pos logit contributions
interstitial+0.333
apult+0.328
anth+0.322
colored+0.319
 Title+0.311
Neg logit contributions
 contrace-0.365
 dstg-0.340
 Krishna-0.318
 Mississ-0.314
 Dru-0.311
Token continue
Token ID2555
Feature activation+3.68e-01

Pos logit contributions
interstitial+0.796
apult+0.794
anth+0.784
colored+0.774
 Title+0.761
Neg logit contributions
 contrace-0.894
 dstg-0.832
 Krishna-0.776
 Mississ-0.770
rists-0.760
Token to
Token ID284
Feature activation+2.93e-02

Pos logit contributions
interstitial+0.250
apult+0.245
anth+0.239
colored+0.237
 Title+0.229
Neg logit contributions
 contrace-0.331
 dstg-0.310
 Krishna-0.292
 Mississ-0.288
 Dru-0.287
Token wre
Token ID30154
Feature activation+5.43e-01

Pos logit contributions
interstitial+0.021
apult+0.021
anth+0.021
colored+0.021
 Title+0.020
Neg logit contributions
 contrace-0.025
 dstg-0.023
 Krishna-0.022
 Mississ-0.021
 Dru-0.021
Token the
Token ID262
Feature activation-2.37e-01

Pos logit contributions
 contrace+0.818
 dstg+0.760
 Krishna+0.710
 Mississ+0.700
 Dru+0.697
Neg logit contributions
interstitial-0.760
apult-0.744
anth-0.729
colored-0.726
 Title-0.703
Token people
Token ID661
Feature activation-7.04e-01

Pos logit contributions
 contrace+0.189
 dstg+0.176
 Krishna+0.163
 Mississ+0.159
 Dru+0.159
Neg logit contributions
interstitial-0.185
apult-0.182
anth-0.179
colored-0.178
 Title-0.174
Token we
Token ID356
Feature activation+3.64e-01

Pos logit contributions
 contrace+0.592
 dstg+0.554
 Krishna+0.515
 Mississ+0.507
 Dru+0.505
Neg logit contributions
interstitial-0.519
apult-0.509
anth-0.497
colored-0.497
 Title-0.483
Token couldn
Token ID3521
Feature activation+7.39e-01

Pos logit contributions
interstitial+0.266
apult+0.264
colored+0.259
anth+0.257
 Title+0.252
Neg logit contributions
 contrace-0.301
 dstg-0.286
 Krishna-0.263
 Dru-0.259
 Mississ-0.257
Token't
Token ID470
Feature activation-6.38e-01

Pos logit contributions
interstitial+0.545
apult+0.534
anth+0.523
colored+0.520
 Title+0.503
Neg logit contributions
 contrace-0.628
 dstg-0.581
 Krishna-0.544
 Mississ-0.538
 Dru-0.535
Token allow
Token ID1249
Feature activation-1.33e+00

Pos logit contributions
 contrace+0.553
 dstg+0.519
 Krishna+0.484
 Mississ+0.478
 Dru+0.477
Neg logit contributions
interstitial-0.452
apult-0.444
anth-0.436
colored-0.434
 Title-0.420
Token ourselves
Token ID6731
Feature activation+8.38e-01

Pos logit contributions
 contrace+1.182
 dstg+1.103
 Krishna+1.038
 Mississ+1.025
 Dru+1.021
Neg logit contributions
interstitial-0.932
apult-0.910
anth-0.890
colored-0.884
 Title-0.853
Token to
Token ID284
Feature activation-8.64e-01

Pos logit contributions
interstitial+0.552
apult+0.540
anth+0.528
colored+0.525
 Title+0.505
Neg logit contributions
 contrace-0.770
 dstg-0.722
 Krishna-0.680
 Mississ-0.672
 Dru-0.671
Token be
Token ID307
Feature activation+2.08e-01

Pos logit contributions
 contrace+0.743
 dstg+0.695
 Krishna+0.650
 Mississ+0.640
 Dru+0.639
Neg logit contributions
interstitial-0.620
apult-0.609
anth-0.595
colored-0.594
 Title-0.574
Token accepted
Token ID6292
Feature activation-7.26e-01

Pos logit contributions
interstitial+0.160
apult+0.158
colored+0.155
anth+0.154
 Title+0.151
Neg logit contributions
 contrace-0.166
 dstg-0.156
 Krishna-0.143
 Mississ-0.141
 Dru-0.141
Token by
Token ID416
Feature activation-3.19e-01

Pos logit contributions
 contrace+0.612
 dstg+0.571
 Krishna+0.532
 Mississ+0.526
 Dru+0.524
Neg logit contributions
interstitial-0.534
apult-0.525
anth-0.513
colored-0.512
 Title-0.496
Token.
Token ID13
Feature activation-4.11e-01

Pos logit contributions
interstitial+0.300
apult+0.294
anth+0.288
colored+0.286
 Title+0.277
Neg logit contributions
 contrace-0.345
 dstg-0.320
 Krishna-0.301
 Mississ-0.297
 Dru-0.295
Tokentv
Token ID14981
Feature activation-2.47e+00

Pos logit contributions
 contrace+0.388
 dstg+0.365
 Krishna+0.345
 Mississ+0.341
 Dru+0.340
Neg logit contributions
interstitial-0.262
apult-0.255
anth-0.248
colored-0.246
 Title-0.236
Token/
Token ID14
Feature activation+9.40e-01

Pos logit contributions
 contrace+2.020
 dstg+1.891
 Krishna+1.772
 Mississ+1.753
 Dru+1.747
Neg logit contributions
interstitial-1.887
apult-1.821
anth-1.776
colored-1.776
 Title-1.691
Tokend
Token ID67
Feature activation+6.62e-01

Pos logit contributions
interstitial+0.658
apult+0.642
anth+0.629
colored+0.625
 Title+0.602
Neg logit contributions
 contrace-0.831
 dstg-0.775
 Krishna-0.730
 Mississ-0.721
 Dru-0.718
Tokenanks
Token ID2283
Feature activation+1.47e+00

Pos logit contributions
interstitial+0.459
apult+0.448
anth+0.438
colored+0.435
 Title+0.419
Neg logit contributions
 contrace-0.590
 dstg-0.551
 Krishna-0.519
 Mississ-0.513
 Dru-0.511
Tokenh
Token ID71
Feature activation-3.64e+00

Pos logit contributions
interstitial+1.018
apult+0.998
anth+0.977
colored+0.968
 Title+0.934
Neg logit contributions
 contrace-1.319
 dstg-1.229
 Krishna-1.157
 Mississ-1.143
 Dru-1.137
Tokenrine
Token ID7640
Feature activation+1.52e+00

Pos logit contributions
 contrace+3.459
 dstg+3.290
 Krishna+3.120
 Dru+3.077
rists+3.075
Neg logit contributions
interstitial-2.231
apult-2.115
colored-2.065
anth-2.043
 Title-2.002
Token Weekly
Token ID18168
Feature activation-5.27e-01

Pos logit contributions
interstitial+1.044
apult+1.023
anth+1.001
colored+0.992
 Title+0.960
Neg logit contributions
 contrace-1.364
 dstg-1.272
 Krishna-1.195
 Mississ-1.183
 Dru-1.176
Token SC
Token ID6374
Feature activation+4.58e-01

Pos logit contributions
 contrace+0.476
 dstg+0.445
 Krishna+0.420
 Mississ+0.415
 Dru+0.413
Neg logit contributions
interstitial-0.359
apult-0.351
anth-0.343
colored-0.340
 Title-0.327
Token2
Token ID17
Feature activation+1.40e+00

Pos logit contributions
interstitial+0.293
apult+0.284
anth+0.279
colored+0.276
 Title+0.267
Neg logit contributions
 contrace-0.435
 dstg-0.406
 Krishna-0.383
 Mississ-0.379
 Dru-0.377
Token Podcast
Token ID16036
Feature activation-5.10e-02

Pos logit contributions
interstitial+0.921
apult+0.897
anth+0.882
colored+0.874
 Title+0.857
Neg logit contributions
 contrace-1.285
 dstg-1.203
 Krishna-1.133
 Mississ-1.116
rists-1.106
Tokenf
Token ID69
Feature activation+6.23e-01

Pos logit contributions
 contrace+0.132
 dstg+0.122
 Krishna+0.115
 Mississ+0.113
 Dru+0.113
Neg logit contributions
interstitial-0.119
apult-0.117
anth-0.114
colored-0.114
 Title-0.110
Token);
Token ID1776
Feature activation+4.99e-01

Pos logit contributions
interstitial+0.508
apult+0.501
anth+0.491
colored+0.489
 Title+0.477
Neg logit contributions
 contrace-0.485
 dstg-0.435
 Krishna-0.407
 Mississ-0.401
 Dru-0.398
Token RAW
Token ID33782
Feature activation-1.25e+00

Pos logit contributions
interstitial+0.461
apult+0.453
anth+0.446
colored+0.444
 Title+0.434
Neg logit contributions
 contrace-0.327
 dstg-0.298
 Krishna-0.274
 Mississ-0.270
 Dru-0.267
Token_
Token ID62
Feature activation+2.12e-01

Pos logit contributions
 contrace+0.999
 dstg+0.944
 Krishna+0.884
 Mississ+0.869
 Dru+0.868
Neg logit contributions
interstitial-0.975
apult-0.950
anth-0.926
colored-0.921
 Title-0.888
TokenASS
Token ID10705
Feature activation-3.69e+00

Pos logit contributions
interstitial+0.156
apult+0.153
anth+0.150
colored+0.149
 Title+0.144
Neg logit contributions
 contrace-0.179
 dstg-0.166
 Krishna-0.156
 Mississ-0.154
 Dru-0.153
TokenERT
Token ID17395
Feature activation-4.26e+00

Pos logit contributions
 contrace+3.517
 dstg+3.466
 Krishna+3.304
 Dru+3.262
 Mississ+3.235
Neg logit contributions
interstitial-2.156
apult-2.000
anth-1.974
colored-1.953
 Title-1.825
Token(
Token ID7
Feature activation-1.76e+00

Pos logit contributions
 contrace+2.956
 dstg+2.856
 Krishna+2.652
 Dru+2.597
 Mississ+2.582
Neg logit contributions
interstitial-3.681
apult-3.573
anth-3.495
colored-3.474
 Title-3.345
Tokenit
Token ID270
Feature activation-2.52e+00

Pos logit contributions
 contrace+1.719
 dstg+1.639
 Krishna+1.552
 Dru+1.529
 Mississ+1.527
Neg logit contributions
interstitial-1.040
apult-1.013
anth-0.972
colored-0.963
 Title-0.935
Token->
Token ID3784
Feature activation+1.17e+00

Pos logit contributions
 contrace+1.793
 dstg+1.760
 Krishna+1.642
 Dru+1.614
 Mississ+1.601
Neg logit contributions
interstitial-2.136
apult-2.048
anth-1.987
colored-1.976
 Title-1.917
Tokenf
Token ID69
Feature activation-1.76e+00

Pos logit contributions
interstitial+0.429
apult+0.407
anth+0.394
colored+0.390
 Title+0.355
Neg logit contributions
 contrace-1.430
 dstg-1.355
 Krishna-1.302
 Mississ-1.290
 Dru-1.287
Token()
Token ID3419
Feature activation+8.35e-01

Pos logit contributions
 contrace+1.587
 dstg+1.487
 Krishna+1.400
 Mississ+1.385
 Dru+1.378
Neg logit contributions
interstitial-1.194
apult-1.164
anth-1.138
colored-1.127
 Title-1.089
Token royalty
Token ID29359
Feature activation+9.56e-01

Pos logit contributions
 contrace+1.230
 dstg+1.139
 Krishna+1.076
 Mississ+1.062
 Dru+1.060
Neg logit contributions
interstitial-1.082
apult-1.059
anth-1.032
colored-1.028
 Title-0.977
Token?
Token ID30
Feature activation+4.57e-01

Pos logit contributions
interstitial+0.672
apult+0.657
anth+0.642
colored+0.638
 Title+0.615
Neg logit contributions
 contrace-0.843
 dstg-0.786
 Krishna-0.740
 Mississ-0.731
 Dru-0.728
Token @
Token ID2488
Feature activation-1.51e+00

Pos logit contributions
interstitial+0.306
apult+0.299
anth+0.293
colored+0.290
 Title+0.281
Neg logit contributions
 contrace-0.417
 dstg-0.390
 Krishna-0.367
 Mississ-0.362
 Dru-0.361
TokenA
Token ID32
Feature activation-1.14e+00

Pos logit contributions
 contrace+1.327
 dstg+1.238
 Krishna+1.167
 Mississ+1.152
 Dru+1.150
Neg logit contributions
interstitial-1.058
apult-1.031
anth-1.001
colored-0.996
 Title-0.963
Tokenjit
Token ID45051
Feature activation-7.30e-01

Pos logit contributions
 contrace+1.064
 dstg+0.997
 Krishna+0.945
 Mississ+0.936
 Dru+0.928
Neg logit contributions
interstitial-0.746
apult-0.719
anth-0.696
colored-0.693
 Title-0.666
TokenP
Token ID47
Feature activation-4.37e+00

Pos logit contributions
 contrace+0.697
 dstg+0.654
 Krishna+0.618
 Mississ+0.611
 Dru+0.609
Neg logit contributions
interstitial-0.459
apult-0.447
anth-0.436
colored-0.433
 Title-0.415
Tokenai
Token ID1872
Feature activation-1.18e+00

Pos logit contributions
 contrace+4.303
 dstg+4.175
 Krishna+3.956
 Dru+3.914
rists+3.891
Neg logit contributions
interstitial-2.457
apult-2.345
colored-2.277
anth-2.196
 Title-2.158
TokenF
Token ID37
Feature activation-1.05e+00

Pos logit contributions
 contrace+1.039
 dstg+0.969
 Krishna+0.912
 Mississ+0.901
 Dru+0.898
Neg logit contributions
interstitial-0.831
apult-0.810
anth-0.792
colored-0.787
 Title-0.758
TokenCC
Token ID4093
Feature activation+3.01e-01

Pos logit contributions
 contrace+0.862
 dstg+0.800
 Krishna+0.751
 Mississ+0.740
 Dru+0.738
Neg logit contributions
interstitial-0.799
apult-0.779
anth-0.762
colored-0.758
 Title-0.731
Tokenorp
Token ID16300
Feature activation-1.24e+00

Pos logit contributions
interstitial+0.220
apult+0.216
anth+0.213
colored+0.211
 Title+0.205
Neg logit contributions
 contrace-0.256
 dstg-0.238
 Krishna-0.224
 Mississ-0.220
 Dru-0.219
TokenSh
Token ID2484
Feature activation-1.77e+00

Pos logit contributions
 contrace+1.080
 dstg+1.006
 Krishna+0.949
 Mississ+0.938
 Dru+0.936
Neg logit contributions
interstitial-0.889
apult-0.864
anth-0.844
colored-0.841
 Title-0.807
Token)
Token ID8
Feature activation-4.74e-02

Pos logit contributions
 contrace+0.246
 dstg+0.225
 Krishna+0.207
 Mississ+0.204
 Dru+0.203
Neg logit contributions
interstitial-0.317
apult-0.312
anth-0.307
colored-0.305
 Title-0.297
Token
Token ID198
Feature activation-7.66e-01

Pos logit contributions
 contrace+0.046
 dstg+0.043
 Krishna+0.041
 Mississ+0.040
 Dru+0.040
Neg logit contributions
interstitial-0.029
apult-0.028
anth-0.028
colored-0.027
 Title-0.026
Token
Token ID198
Feature activation+8.16e-02

Pos logit contributions
 contrace+0.744
 dstg+0.723
 Krishna+0.689
 Dru+0.681
 Mississ+0.680
Neg logit contributions
interstitial-0.457
apult-0.436
anth-0.418
colored-0.416
 Title-0.390
TokenO
Token ID46
Feature activation-4.20e-03

Pos logit contributions
interstitial+0.057
apult+0.055
anth+0.054
colored+0.054
 Title+0.052
Neg logit contributions
 contrace-0.073
 dstg-0.068
 Krishna-0.064
 Mississ-0.063
 Dru-0.063
Tokenpin
Token ID11635
Feature activation+5.18e-01

Pos logit contributions
 contrace+0.004
 dstg+0.004
 Krishna+0.003
 Mississ+0.003
 Dru+0.003
Neg logit contributions
interstitial-0.003
apult-0.003
anth-0.003
colored-0.003
 Title-0.003
Tokenion
Token ID295
Feature activation-3.67e+00

Pos logit contributions
interstitial+0.475
apult+0.470
anth+0.462
colored+0.458
 Title+0.448
Neg logit contributions
 contrace-0.347
 dstg-0.313
 Krishna-0.288
 Mississ-0.283
 Dru-0.279
Token (
Token ID357
Feature activation+6.23e-01

Pos logit contributions
 contrace+3.082
 dstg+2.868
 Krishna+2.708
 Dru+2.671
 Mississ+2.660
Neg logit contributions
interstitial-2.729
apult-2.636
anth-2.576
colored-2.562
 Title-2.446
Tokenby
Token ID1525
Feature activation+5.33e-01

Pos logit contributions
interstitial+0.477
apult+0.465
anth+0.460
colored+0.457
 Title+0.440
Neg logit contributions
 contrace-0.513
 dstg-0.475
 Krishna-0.444
 Mississ-0.438
 Dru-0.436
Token Jesse
Token ID18033
Feature activation-3.96e-01

Pos logit contributions
interstitial+0.412
apult+0.405
anth+0.399
colored+0.395
 Title+0.385
Neg logit contributions
 contrace-0.430
 dstg-0.397
 Krishna-0.369
 Mississ-0.366
 Dru-0.363
Token Smith
Token ID4176
Feature activation+7.56e-01

Pos logit contributions
 contrace+0.385
 dstg+0.362
 Krishna+0.343
 Mississ+0.339
 Dru+0.338
Neg logit contributions
interstitial-0.243
apult-0.236
anth-0.230
colored-0.228
 Title-0.218
Token)
Token ID8
Feature activation+3.36e-01

Pos logit contributions
interstitial+0.606
apult+0.596
anth+0.586
colored+0.581
 Title+0.566
Neg logit contributions
 contrace-0.589
 dstg-0.544
 Krishna-0.507
 Mississ-0.499
 Dru-0.497
Token billion
Token ID2997
Feature activation-1.19e+00

Pos logit contributions
interstitial+0.351
apult+0.343
anth+0.337
colored+0.335
 Title+0.323
Neg logit contributions
 contrace-0.406
 dstg-0.377
 Krishna-0.353
 Mississ-0.349
 Dru-0.347
Token years
Token ID812
Feature activation-1.61e+00

Pos logit contributions
 contrace+0.931
 dstg+0.862
 Krishna+0.805
 Mississ+0.795
 Dru+0.790
Neg logit contributions
interstitial-0.953
apult-0.931
anth-0.911
colored-0.906
 Title-0.876
Token after
Token ID706
Feature activation-1.10e+00

Pos logit contributions
 contrace+1.338
 dstg+1.243
 Krishna+1.171
 Mississ+1.157
 Dru+1.148
Neg logit contributions
interstitial-1.200
apult-1.173
anth-1.145
colored-1.144
 Title-1.100
Token the
Token ID262
Feature activation-5.37e-02

Pos logit contributions
 contrace+0.864
 dstg+0.799
 Krishna+0.747
 Mississ+0.737
 Dru+0.733
Neg logit contributions
interstitial-0.875
apult-0.856
anth-0.839
colored-0.835
 Title-0.807
Token Big
Token ID4403
Feature activation-1.37e+00

Pos logit contributions
 contrace+0.053
 dstg+0.050
 Krishna+0.047
 Mississ+0.046
 Dru+0.046
Neg logit contributions
interstitial-0.032
apult-0.031
anth-0.031
colored-0.030
 Title-0.029
Token Bang
Token ID9801
Feature activation-4.15e+00

Pos logit contributions
 contrace+1.246
 dstg+1.164
 Krishna+1.096
 Mississ+1.082
 Dru+1.078
Neg logit contributions
interstitial-0.930
apult-0.909
anth-0.888
colored-0.883
 Title-0.852
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
 contrace+3.134
 dstg+2.884
 Krishna+2.744
 Dru+2.702
 Mississ+2.696
Neg logit contributions
interstitial-3.391
apult-3.246
colored-3.201
anth-3.166
 Title-3.049
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
interstitial+0.106
apult+0.103
anth+0.101
colored+0.100
 Title+0.095
Neg logit contributions
 contrace-0.166
 dstg-0.156
 Krishna-0.148
 Mississ-0.146
 Dru-0.146
Token
Token ID198
Feature activation+7.32e-02

Pos logit contributions
interstitial+0.058
apult+0.056
anth+0.054
colored+0.054
 Title+0.051
Neg logit contributions
 contrace-0.103
 dstg-0.099
 Krishna-0.094
 Mississ-0.093
 Dru-0.093
Token
Token ID447
Feature activation+3.48e-01

Pos logit contributions
interstitial+0.045
apult+0.044
anth+0.043
colored+0.043
 Title+0.041
Neg logit contributions
 contrace-0.070
 dstg-0.066
 Krishna-0.063
 Mississ-0.062
 Dru-0.062
Token
Token ID250
Feature activation+4.69e-01

Pos logit contributions
interstitial+0.229
apult+0.223
anth+0.218
colored+0.216
 Title+0.208
Neg logit contributions
 contrace-0.323
 dstg-0.302
 Krishna-0.285
 Mississ-0.282
 Dru-0.281